Ask HN: Who wants to be hired? (August 2026)
Share your information if you are looking for work. Please use this format:
Location:
Remote:
Willing to relocate:
Technologies:
Résumé/CV:
Email:
Readers: please only email these addresses to discuss work opportunities.
Searchers: try https://nthesis.ai/public/hn-wants-to-be-hired, https://www.wantstobehired.com.
674 comments
[ 0.25 ms ] story [ 34.8 ms ] threadRemote: Yes
Willing to relocate: No
Email: logandark@logandark.net
I am a full-stack software engineer with about 3 years of professional experience. I'm self-taught for about 10 years before I got into the industry. My favorite technologies are Rust, TypeScript and Swift. On the front-end, I have experience in vanilla JS, React.js, Svelte and Angular. (Some jQuery before then.) On the back-end, I have experience in TypeScript on Node.js, Python, various web and application servers and reverse proxies, firewalls, and some databases.
I am opening to learning new frameworks and technologies. I picked up Java/Kotlin for Minecraft modding, I picked up C# for Unity modding, and I was an avid tinkerer with rooted devices (though I do not use them anymore). I will generally pick up any knowledge I need to get something done even if it is something I have never done before. That has not changed in the age of LLMs; I am obsessively critical of their outputs and work hard to understand everything they do. I have done manual work on inference tooling to better understand their inner workings as well.
I have run my own website since I was 12, and owned my own servers since I was 13. My operating system of choice is macOS because it feels better organized than Windows or Linux. I also prefer the profiler tooling that is available on macOS and not Windows. Micro-optimization is one of my pastimes. I manage my own home network, my developer tooling, and personal forks of open-source software.
One of my dreams is to move to a city with faster internet. I am located in the US which is unfortunately notorious for monopolies and anti-consumer practices.
I am available to interview immediately and can start immediately. I am looking for a full-time software engineering role. Please contact me with any interview opportunities.
Remote: Yes
Willing to relocate: Yes
Technologies: JavaScript, Cloudflare Workers, LLM integration, JSDoc
Résumé/CV: kol3x.com
Email: hackernews@kol3x.com
I started as a fullstack JS engineer and grew into product development at my last company. I owned the ingestion layer - collecting 100k relevant messages/month from 4 platforms through a dirt-cheap serverless back-end on Cloudflare Workers.
We worked with LLMs deeply, especially in code generation. I was part of a small team developing SpecGEM, a fine-tuned model that generates Cloudflare Workers code from JSDoc comments and is designed to outperform mainstream LLMs at this narrow task.
I just released an open-source self-hosted LLM assistant on Cloudflare Workers that predictably compounds context across conversations. https://github.com/kol3x/pawmc
Looking for a remote role where I can own work end-to-end. Stack-wise I'm strongest on Cloudflare Workers, JavaScript, and practical LLM integration.
CV, LinkedIn, and GitHub are also linked at https://kol3x.com
Remote: Yes
Willing to relocate: No
Technologies: Python, web scraping and data extraction, ETL pipelines, Playwright, BeautifulSoup, Tesseract OCR, PostgreSQL, SQLite, pytest, GitHub Actions, Astro, Cloudflare Pages, C / ESP-IDF, NumPy
Résumé/CV: https://braedenkeena.pages.dev
Email: braeden@thekeenas.com
I build data pipelines that know when they're lying to you.
GAScout (https://gascout.pages.dev) — Georgia public-records pipeline. Four counties live, each a different ingestion problem resolved into one schema: a 9,915-page fixed-width mainframe PDF (409,142 records, zero dropped rows), a weekly XLSX roll, monthly text PDFs, and scanned sheriff's levy documents via OCR. Adding a county is a config file, not code. The other 155 are labeled planned rather than filled with invented numbers.
FindStorage (https://findstorage.pages.dev) — national self-storage pricing tracker. 4,639 locations, 245,000+ price changes logged, running unattended on a daily schedule. Aborts rather than publishing when the store count moves more than it should, because the failure that costs you isn't a crash — it's a scraper quietly returning less after a site changes and nobody noticing for three weeks.
Also built a WiFi CSI device-fingerprinting array on ESP32 — custom ESP-IDF firmware and a Python DSP pipeline, running as my apartment's security system. Cross-manufacturer separation holds at 11-15 sigma; same-model discrimination tops out near 77% and true clock twins are the open problem.
Before this I ran a 500-acre motocross park in Northern California: acquired dormant land, re-entitled it, directed a 120-person race-day crew, ran the medical plan through a mid-event helicopter evacuation, and sold my stake.
Self-taught, ~18 months in. Interested in data engineering, pipeline work, and anything where messy real-world sources have to become trustworthy structured data.
Remote: Yes, or hybrid if nearby
Willing to relocate: Possibly
Technologies: Python, Ruby, C, C++, C#, JavaScript, TypeScript, PowerShell, Flask, SQL, PostGIS, Shapely, Unity, Unreal Engine, multiple assembly/machine languages, Windows user code and kernel drivers, Google Maps and other map APIs, geographic and airspace data
Résumé/CV: https://www.geary.com/resume.html or https://www.geary.com/resume.pdf and https://www.linkedin.com/in/michaelgeary/
Email: mike@geary.com
Hi, I'm Michael Geary. I've programmed in many languages and environments over the years. Some of my current interests are:
• Developer experience. I love helping my fellow developers solve problems, and building tools to make their jobs easier and more enjoyable.
• Aviation and geographic data. For example, airspace and obstacle data importers for Wing; election results and voter information maps for Google; many interactive maps for other companies.
• Hardware interfacing. In a way, I am a "full stack" developer, but my stack may involve a front end to a piece of hardware rather than the cloud. I first got into programming via ham radio, so RF hardware remains an interest.
• Designing and building APIs. Too often an API is designed by exposing the internals of whatever system provides the API. My philosophy is the opposite: start with the apps. I like to build a series of sample apps before starting on the API. This way I can imagine what API will make those apps and others like them easy to build.
• Talk with users! I don't like to sit in a back room cranking out code. I want to make sure it's the right code for what my users need, and that it's easy to maintain and improve as we learn more about what they want.
Open to full time or contract.
I look forward to talking with you!
Technologies: Agentic Engineering (Claude, Codex, Cohere, Voyage, Mistral, LangChain, LanceDB, LLaMA, Mistral), C/C++/Rust/Node/Typescript/React/Python, Azure/AWS/Docker/K8S, DevOps tooling, ML/BigData/Search tooling ... and much more
Résumé/CV: https://www.artifixsolutions.com?sid=hn202608. Email: lajos [@] artifixsolutions.com
WHO: Technology Polymath. Agentic context & harness engineering.
WHAT: Whether human or AI built, I know how systems break. I build them so they don't. After three decades of battle-tested experience there isn't a failure mode I don't know how to fix. When it comes to AI, I design and architect systems using my own rigorous engineering approach that insures consistent delivery and drift control.
SAMPLE WORK:
I work with companies and teams who honestly want to deliver the best product they can. I'm serious about my work and I work only with equally serious people. If you want systems built right the first time, I'm your guy.I built and operate a 106k+ LOC production SaaS on Next.js 15, Supabase and Stripe — solo. Zero "any" types in the whole codebase, 743 passing tests.
What I'm actually good at is the part that breaks after launch: the webhook replay, the downgrade that never revokes access, the export gated only in the browser, the URL fetch that can reach your metadata endpoint. I've put my own codebase through repeated adversarial audits and can share a redacted report — real findings, real severities, subject anonymised.
Available ~20-30 hrs/week, UTC+0 — good overlap with European hours and US mornings. Contract or fixed-scope. I also do fixed-price pre-launch audits (security, billing correctness, data exposure) if that's more useful than hourly.
Full-stack engineer, 8 years, front-end deep, CET. I take over live systems and restructure them without stopping the roadmap. At Jebbit (L'Oreal, AutoZone, NFL, ~1M sessions/hour) I led a four-month refactor that replaced a per-row style override system with one merged JSON schema, backwards compatible with both running in parallel. Currently on a consumer AI product where I own features end to end and took page load from 3s to 1.5s and a deep component from ~300 re-renders to ~10.
AI-native: I don't hand-write much anymore, I spec work and drive agents against it, and spend my time on judgment and review. Claude Code and Cursor daily.
Location: Vermont, USA
Remote: Yes (open to travel)
Willing to relocate: No
Technologies: TypeScript, Node.js/Deno, PostgreSQL, Redis, AWS, React, Elasticsearch, Databricks/Spark, FFmpeg
Résumé/CV: https://en.masher.media/about.html
Email: hn.57@masher.media
I’ve spent about half my time in first/founding engineer roles at startups, and half working directly for clients, agencies, and institutions on a wide variety of products. Folks enjoy my enthusiasm for their ideas and my ability to meet them where they are technically, always providing that extra context that builds trust and understanding.
I’m comfortable owning concerns end-to-end, from initial scoping and architectural tradeoffs through deployment of functional prototypes and user testing. I enjoy iterating and scaling systems from there, while building teams to maintain and build upon them.
Expertise in database design, media rendering systems, engagement platforms, high-volume event ingestion, ML pipelines, and getting it all working in AWS. Top priorities are data integrity, security, and privacy.
Lean on me for:
- Technical scoping and planning for a new product or platform before committing resources
- Architectural review and data modeling to see how a system should flow and which tradeoffs matter
- Greenfield builds where you need someone to plan and ship v1 without much hand-holding
- Forward-deployed engineering, working directly with potential customers to help guide the product
Pragmatic about LLMs: effective for exploration, debugging, documentation, and tightly scoped implementation work when paired with strong engineering judgment and rigid testing.
Remote: Yes
Willing to relocate: No
Technologies: TypeScript, JavaScript, Angular, RxJS, React, Web Components (Lit), Node.js, PostgreSQL, AWS, Docker, GitHub Actions, Playwright, Jest, Vitest
Résumé/CV: https://martomo.nl/Martijn-Dijkhuizen-CV_2026.pdf
LinkedIn: https://www.linkedin.com/in/martijndijkhuizen/
Email: hello@martomo.nl
--------------
A passionate problem solver with over fifteen years of experience, currently a founding engineer at a self-funded startup building a design and prototyping tool. Before that, I worked mainly as a full-stack engineer at SaaS companies.
Problem solving for me does not stop at the product/code, I'm always finding ways to improve the development process or help colleagues get unstuck by mentoring and coaching. Also I'm not afraid to learn a new programming language/framework or to dive into the infrastructure.
Are you looking for a seasoned, product-oriented software engineer who cares about user experience and can drive a feature from idea to implementation?
I've been working for equity and now I'm looking for a full-time, long-term remote role that pays. Preferably with a SaaS company working in European time zones (CET/CEST +/- 2 hours).
I fluctuate between:
- Deep learning / Neural networks - from architecture to inference. You might have used my ♥ Lovely Tensors library if you work with PyTorch (or JAX). Some CUDA, pytorch profiler, etc.
https://github.com/xl0/lovely-tensors https://github.com/xl0/lovely-jax https://github.com/xl0/lovely-numpy
https://github.com/xl0/tidygrad https://github.com/xl0/latent-tools https://github.com/xl0/nvml-tool
- Full-stack AI-adjacent applications - the usual LLM API tool-calling "agentinc" AI + full-stack web, ideally with SvelteKit (typescript, tailwind, shadcn, drizzle, etc).
https://chat.congusto.ai/chat https://lovely-docs.github.io https://pelican.alexey.work/gallery
In my past lives: Linux kernel development, Molecular Biology Masters degree, Electronics engineering in Shenzhen: https://alexey.work/cv?ref=49156682&view=full
Remote: Yes (Worldwide)
Willing to relocate: No
Technologies: Angular, Java, Spring Boot, REST APIs, LLM Engineering, Microservices, TypeScript, JavaScript, React, Node.js, SQL, AWS (EC2, S3), Git, CI/CD, Playwright, JUnit, AI Agents, RAG, MCP, Power Platform
Resume: https://drive.google.com/file/d/1VS9YQ6Hvz3Pw62RSjwQa7fe-Imy...
GitHub: https://github.com/harshvardhan-vhatkar
LinkedIn: https://www.linkedin.com/in/harshvardhan-vhatkar/
Email: harshuvhatkar@gmail.com
Software Engineer with 3+ years of experience building frontend applications, backend services, automated testing pipelines, and AI-powered developer tools. At my current company, I've improved Angular applications, built Spring Boot microservices with 100% unit test coverage, automated Playwright regression testing (reducing execution time from 2 hours to 30 minutes), and developed an AI-powered MCP server that generates Playwright tests from natural language, reducing test authoring from 45 minutes to under 2 minutes per spec. I enjoy building products end-to-end rather than working on isolated tickets. Recently I've been focused on AI developer tooling, RAG pipelines, MCP servers, and LLM-powered automation alongside traditional backend development.
Some highlights:
• Spring Boot microservices and REST APIs
• Angular, React, Next.js, Node.js
• AI Agents, MCP, RAG pipelines, vector databases
• Playwright automation and developer productivity tools
• AWS, CI/CD, SQL
I'm looking for a remote backend, full-stack, or AI engineering role where I can own features, work closely with a product team, and build software that ships to users. Startups and product companies are especially interesting.
If you're looking for an engineer who enjoys solving problems, automating repetitive work, and shipping production-ready software, I'd love to talk.
Remote: Preferred.
Technologies: AWS, EKS, GitHub Actions, crossplane, Terraform, Azure DevOps, EC2.
Resume/CV: linkedin.com/in/lsdir
Email: elliotechne42@gmail.com
GitHub: https://github.com/autotune
Remote: primarily, willing to travel to meet and collaborate
Willing to relocate: no
Technologies: Python, Go, Kotlin, Java, Swift, TypeScript, AWS, GCP, Terraform, PostgreSQL, Redis
Résumé/CV: https://robinsiep.com/experience
Email: contact [at] robinsiep.com
I’m a senior engineer and software architect used to working with teams that are starting to strain under growth, complexity, or delivery pressure.
Over the last ~10 years I’ve been working with startups and established companies, primarily in roles where I take end-to-end technical responsibility: from system design through implementation and production operation, while remaining hands-on in delivery.
Recent work includes leading the architecture, implementation, and operational ownership of a distributed platform for venture capital workflows, as well as building and maintaining a survey fulfillment system. Both engagements included mentoring and coordinating engineers alongside delivery. More details can be found at https://robinsiep.com.
I'm currently interested in finding a more permanent role, but remain available for contract work in the meantime.
Remote: Yes
Willing to relocate: No
AI Product Engineering: full-stack AI systems, LangGraph/Chain, RAG
Technical: TypeScript, Node.js, Python, React/Vue, PostgreSQL, vector DBs, NoSQL, AWS, GCP
Recent work includes:
• multilingual AI product (26 languages) for search automation
• AI-assisted incident intelligence platform for enterprise security teams
• multi-tenant account management platform (Life Alert providers)
• semantic video search using multimodal embeddings
• multi-agent systems integrating LLMs with internal data, docs, and APIs
Experience helping teams move LLM / agent workflows (incl. LangGraph/Chain) from prototype >> production.
Previously founded and exited a SaaS company serving Fortune 500 brands (pricing intelligence & channel compliance), built and led distributed team of 100+.
LinkedIn: https://www.linkedin.com/in/jeff-borden/
Email: jborden13 [@t] gmail [dot] com
* Open to full-time, fractional, or advisory roles.
Remote: Yes
Willing to relocate: No
Technologies: Ruby, Ruby on Rails, PostgreSQL, Sidekiq/Redis, Hotwire, JavaScript, TypeScript, React, GraphQL/REST/Grape, RSpec/Capybara, Python/FastAPI, PyTorch/Hugging Face, LLM APIs (OpenAI, Anthropic), Docker, AWS/DigitalOcean
Résumé/CV: https://katatsu12.github.io/
Email: den.zubrytskyi@gmail.com
---
Senior full-stack Rails engineer, 9 years commercial. I ship AI features into production SaaS — not demos.
Most recent: Review Copilot, an AI review-analytics app live on the Shopify App Store, built and shipped solo end to end. Rails 8 backend, plus a DistilBERT multi-label classifier I fine-tuned via knowledge distillation and serve from a Python/FastAPI microservice, orchestrated through Sidekiq. Every recommendation cites the reviews behind it, with a verification pass that flags claims the underlying feedback doesn't support.
Before that: an AI-driven ABM platform (Rails + React) with LLM content-generation pipelines, marketplace products with payments and geolocation, and a legacy CoffeeScript → Turbo Frames migration.
Looking for senior IC work on a Rails product — ideally somewhere LLM or ML features are on the roadmap rather than bolted on.
Location: Kyiv, Ukraine. Remote: Yes. Willing to relocate: No.
Technologies: Angular (AngularJS, v13 > v21), React, Next.js, Vue, TypeScript, RxJS, Node.js, PostgreSQL. 6+ years across fintech, healthcare, and marketing SaaS.
Full-cycle development or targeted fixes — whichever the project needs. I ship clean work in complex production codebases without breaking the rest.
LinkedIn: https://www.linkedin.com/in/denys-derkach
Resume/CV: https://drive.google.com/file/d/1npiW3bEzxLh11KPqQFHlouvDxQR...
Email: podstavka128@gmail.com
Remote: Yes (100% Remote only)
Willing to relocate: No
Technologies: LLM Context Architecture, System Analysis, Prompt/Logic Orchestration, Unstructured Data Forensics
Résumé/CV:
- Role: AI Systems Analyst (Concept & Orchestration)
- Focus: Designing structural logic frameworks and external control layers to solve core LLM limitations in heavy enterprise environments — eliminating Lost-in-the-Middle failures and context rot (no traditional production coding).
- Deliverables: Deterministic LLM Context Architectures for 500+ page docs, stochastic drift/hallucination prevention via audit layers, advanced pattern and anomaly detection (Rongorongo, Kryptos, Dorabella, Voynich).
- Terms: German employment contract & benefits (Open to international via EoR / German entity)
- Languages: Native German, fluent written English (async-first)
- Notice Period: 2 months to end of month (German standard)
- LLM Context Architecture Repo: https://github.com/Recursive-Logic-Core/LLM-Context-Architec...
- System Analysis & Forensics Repo: https://github.com/Recursive-Logic-Core/system-analysis
Email: arch_mmm@proton.me
Remote: Yes (Remote/Hybrid depending on location)
Willing to relocate: No
Technologies: Primarily Typescript, React, Bash, GitHub Actions
Résumé/CV: https://punkbit.com/docs/cv-punkbit-helder-oliveira.20260713...
Email: info (at) punkbit (dot) com
I'm a Product Engineer and a creative based in London. I’ve built full-stack applications across web, mobile, blockchain and embedded platforms. My client-side work includes React, Electron, Roku’s Scenegraph, and native iOS development with Swift and SwiftUI, always with a strong focus on UX and design-first thinking. On the service-side, I’ve worked with traditional service hosting, containers, and serverless, including (but not limited to) AWS, GCP, Cloudflare, Workers, CloudFormation, SAM CLI, nodejs, bunjs, MySQL, Postgres, NoSQL, grpc, Redis, Docker, nginx, and a few legacy tools best left unnamed (yes, including CodeIgniter and ftp).
I’ve also developed developer tools like CLIs and SDKs, primarily Typescript/JavaScript land, and have written code in systems languages such as Rust and Zig.
I care about great UX, developer experience, documentation, rapid iteration and automating workflows with CI/CD (GitHub Actions, Bash scripts, etc).
Also familiar with modern development practices by leveraging coding agents, such as pi, opencode, claude and LLM, including kimi over fireworks inference.
Want to know more? https://punkbit.com
Remote : Yes
Willing to relocate : No
Technologies : Go, Python, Django, Docker, Kubernetes, Linux, AWS, Terraform, Helm, GitLab CI/CD, PostgreSQL, SQL/NoSQL, Bash, Angular, Vue.js, React, GIS (ESRI, GeoServer), PostGIS, TDD
Resumé/CV: https://tinyurl.com/jared-a-rodriguez-resume
Email: jaredarodriguez@gmail.com
Backend and cloud-native platform engineer with 5+ years of experience building production APIs, distributed systems, Kubernetes platforms and Infrastructure as Code. I've built REST services in Django and Go, designed a Kubernetes-native workflow orchestration platform used by U.S. National Laboratories for predictive national critical infrastructure analysis, developed custom Kubernetes Operators and automated cloud infrastructure on AWS using Terraform, Docker, Helm and GitLab CI/CD. I enjoy solving backend and platform problems, designing APIs, building developer tooling, automating deployments and approaching development with a test first mentality. Lately I've been focused on Go, Kubernetes internals, observability and the intersection of platform engineering and AI infrastructure.
Remote: Yes
Willing to relocate: No
Technologies: React, Next.js, Node.js, Three.js, React native,
Portfolio:https://beaded-desk-2c0.notion.site/Portfolio-23ea526e5bbc40...
Email: kaths2651@gmail.com
Discord: kathan2651
Heya, I am a developer with 4+ years of experience working with React, Next.js and node.js. I have written some blogs about things I built.
I am always up for learning new things and applying it,if you are looking for someone who can be in your niche tech or something challenging,Then I am your guy.
Other than that, I love movies and books, mainly stories, world building, fantasy, and that would be awesome if I got a chance to work on anything in this
Interested in Job as well contract/freelance work.
Thanks :)
Remote: Yes (or hybrid)
Willing to relocate: Yes
https://joecardoso.dev
What I do: I build agentic systems and full-stack infrastructure.
Recent work:
- Founding contributor at NimbleBrain: designed the agentic loop and workflow engine that guides AI agents through building and publishing MCP server integrations end-to-end
- Co-created Vispyr: self-hosted observability platform on AWS with automated infra provisioning, OTel instrumentation, and a full Grafana telemetry stack
- Mozilla Firefox contributor: accessibility and DevTools CSS refactors
Stack I reach for: Python, TypeScript, AWS, Docker, PostgreSQL, Grafana stack, OpenTelemetry, MCP
AI-native: I build with Claude Code daily. Comfortable across the agentic toolchain — RAG, vector DBs, MCP, context engineering.
Resume: https://drive.google.com/file/d/179YWmLYuUz9Cfd-aOLGcgKpWbuz...
Email: jow13_122@yahoo.com
Profile: I'm a Canadian citizen Full-Stack SWE co-creator of Vispyr, an end-to-end, self-hosted, observability tool with automated infrastructure deployment, contributor to Mozilla Firefox, and a founding contributor to NimbleBrain.
Remote: Yes
Willing to relocate: No
Technologies: Rust, Golang, Python (Django, Scikit-learn, Pandas), PostgreSQL, Clickhouse, Elasticsearch, Docker, GCP.
Résumé/CV: Reach out and I’ll send a detailed version
Email: check my profile
Senior Software Engineer with 11+ years of experience building and scaling distributed systems.
My career has spanned high-growth startups, successful acquisitions, and major enterprise research labs.
Willing to Relocate: Yes, to Barcelona, Roma, Hamburg, Koln, Den Haag, Amsterdam, Rotterdam, Stockholm or Switzerland.
Full Remote: Yes. I offer a discount for full-remote work, because it saves me the hassle of relocation and commuting :)
Technologies: Go, Rust, C, Elixir, JavaScript, TypeScript, Python, web technologies (HTML/CSS, frameworks, browser APIs), Bash, Zsh, Fish, Linux, FreeBSD, MySQL, SQLite, PostgreSQL, Redis, Kafka, Docker, mathematics
Email: achenet@fastmail.com
Website: https://arielche.net/
I am a software developer and researcher with half a decade of experience and a Master's degree in mathematics. I have ample experience with Golang in a professional context often on backend services like REST APIs and programs interacting with databases and message queues, am fairly proficient with a variety of other languages and technologies, and am comfortable working on a variety of domains, from accounting/financial management/CRM software, to IaaS products, to scientific and mathematical software and language apps. I enjoy learning, and am always open to learning new things, especially if they happen to ignite my curiosity.
I like free or open-source software, systems programming, web services and the infrastructure required to run them at scale and would love an opportunity to continue to contribute to and learn about them. I enjoy mathematics and quantitative research like biology, engineering and physics. I enjoy writing, and in particular writing documentation for software, educational content, and research.
I am happiest working with people who are open-minded, conscientious and kind, and I try very hard to always embody those qualities.
I am open to both full-time employment and contract work. I am a French citizen and can work freely anywhere within the EU.
Compensation for in person work is location-dependent, and more expensive than full-remote work, due to the extra work involved (physical, moving things around in meatspace work, not just pushing bits around cyberspace). That said, I do really enjoy being in nice offices and hanging out with the team while working, and also really enjoy occasional "team in-person meetups" even when working in a full-remote context.
Remote: Yes — remote only (~EU hours or async)
Willing to relocate: No
Technologies: Python, LLMs & embeddings, semantic search, deterministic data pipelines, PDF/document extraction, OCR
Résumé/CV: https://walat.eu/cv/
Email: dariusz@walat.eu
Trustworthy output from untrustworthy data. I build systems that catch what's silently wrong — a dead sensor nobody noticed, contradictory records, a garbled scan, a confidently-wrong model — so it surfaces as a flag today, not a six-month catastrophe.
I use LLMs where they earn their place (development, meaning, embeddings, plain-language access to jargon-locked data) and keep them out of decisions and the data flow, which stay deterministic and verifiable. An LLM can help you find the answer; it can't be the answer.
Senior systems engineer, multiple AI cycles of judgment on what survives the hype and where it breaks. Currently turning messy Polish legal PDFs into a correctness-checked graph — the hard part is the verification, not the AI. Previously I built a legislative-notification service that ran autonomously in production for over three years before I retired it. I've written about where AI coding agents actually fail and why verification is the real work: https://walat.eu
Best fit when: correctness matters, the data is real-world-messy, and you want someone who names what doesn't work and why.