stakent

Résumé/CV: https://walat.eu/cv/ | https://linkedin.com/in/dariusz-walat

Email: [email protected]

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.

Résumé/CV: https://walat.eu/cv/ | https://linkedin.com/in/dariusz-walat

Email: [email protected]

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.

Résumé/CV: https://walat.eu/cv/ | https://linkedin.com/in/dariusz-walat

Email: [email protected]

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.

Résumé/CV: https://walat.eu/cv/

Email: [email protected]

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.

Résumé/CV: https://walat.eu/cv/

Email: [email protected]

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.

Resume: https://linkedin.com/in/dariusz-walat

Email: [email protected]

Senior Software Engineer with 20+ years building systems that can't fail — from industrial control to modern distributed architectures.

Currently building a production SaaS solo using AI coding agents as primary development method.

Documenting the operational realities — not the marketing: walat.eu/series/ai-agents-in-practice

Looking for remote-first senior IC roles where reliability and technical judgment matter.

Resume: https://linkedin.com/in/dariusz-walat

GitHub: https://github.com/stakent

Email: [email protected]

Senior Software Engineer with 20+ years building systems that can't fail - from industrial control to modern distributed architectures.

Unique value: Industrial reliability mindset + modern tech + highly efficient AI capabilities.

Looking for: Remote-first senior IC roles with interesting technical challenges. Particularly interested in Python/Go positions where reliability matters.

Resume: https://linkedin.com/in/dariusz-walat

GitHub: https://github.com/stakent

Email: [email protected]

Senior Software Engineer with 20+ years building systems that can't fail - from industrial control to modern distributed architectures.

Unique value: Industrial reliability mindset + modern tech + emerging AI capabilities.

Looking for: Remote-first senior IC roles with interesting technical challenges. Particularly interested in Python/Go positions where reliability matters.

Resume: https://linkedin.com/in/dariusz-walat

GitHub: https://github.com/stakent

Email: [email protected]

Senior Software Engineer with 20+ years building systems that can't fail - from industrial control to modern distributed architectures.

Unique value: Industrial reliability mindset + modern tech + emerging AI capabilities.

Looking for: Remote-first senior IC roles with interesting technical challenges. Particularly interested in Python/Go positions where reliability matters.

Resume: https://linkedin.com/in/dariusz-walat

GitHub: https://github.com/stakent

Email: [email protected]

Senior Software Engineer with 20+ years building systems that can't fail - from industrial control to modern distributed architectures.

Unique value: Industrial reliability mindset + modern tech + emerging AI capabilities.

Looking for: Teams deploying AI/ML in production. I've documented systematic agent failure modes from building production systems - see walat.eu/series/ai-agents-in-practice/

Resume: https://linkedin.com/in/dariusz-walat

GitHub: https://github.com/stakent

Email: [email protected]

Senior Software Engineer with 20+ years building systems that can't fail - from industrial control to modern distributed architectures.

Unique value: Industrial reliability mindset + modern tech + emerging AI capabilities.

Looking for: Teams deploying AI/ML in production. I've documented systematic agent failure modes from building production systems - see walat.eu/series/ai-agents-in-practice/

Resume: https://linkedin.com/in/dariusz-walat

GitHub: https://github.com/stakent

Email: [email protected]

Senior Software Engineer with 20+ years building systems that can't fail - from industrial control to modern distributed architectures.

Unique value: Industrial reliability mindset + modern tech + emerging AI capabilities.

Looking for: Remote-first senior IC roles with interesting technical challenges. Particularly interested in Python/Go positions where reliability matters.

Resume: https://linkedin.com/in/dariusz-walat

GitHub: https://github.com/stakent

Email: [email protected]

Senior Software Engineer with 20+ years building systems that can't fail - from industrial control to modern distributed architectures. Currently exploring AI/ML through personal projects (Sejm-Whiz - Polish legal document analysis using NLP).

Unique value: Industrial reliability mindset + modern tech + emerging AI capabilities.

Looking for: Remote-first senior IC roles with interesting technical challenges. Particularly interested in Python/Go positions where reliability matters.