AI and data architecture, beyond the hype. I build the full stack beneath production AI — the data pipelines, the ML, and the LLM systems on top of them — so what ships is correct under failure, secure by design, and cost-bounded at scale, not just impressive in a demo.
You get architectures grounded in computer-science fundamentals and proven in production — designed for what actually decides whether AI survives contact with the real world: performance, security, explainability, and cost. I work with teams where AI has to deliver measurable value and stay trustworthy under real conditions — resilient, monitored, and honest about its failure modes. My approach blends rapid prototyping with production-grade rigor, so you move fast without quietly accumulating technical risk.
PhD in Computer Science, 2015
University of Fribourg -- Switzerland
MSc in Computer Science, 2010
University of Lodz - Poland
MSc in Computer Science, 2009
Université Claude Bernard (Lyon I) - France
BSc in Computer Science, 2006
WIT under the auspices of Polish Academy of Sciences
End-to-end AI and data systems that hold up in production
Roadmaps, feasibility calls, architecture decisions, and hands-on leadership of cross-functional teams — so a project doesn’t over-build or ship something that won’t survive production.
Multi-stage extraction, agentic and deterministic workflows, and structured output with verification — engineered to stay correct under real load, not just demo well.
Noisy, unstructured inputs turned into structured results reliable enough to act on — with provenance and honest failure modes.
Event-driven and batch pipelines, orchestration, validation, and observability — the backbone that decides whether AI is reliable at scale, because it’s rarely the model that fails first.
Defense-in-depth, prompt-injection hardening, and multi-tenant isolation for regulated and sensitive-data environments.
An honest POC that predicts production before the expensive build, then the engineering to ship it and keep it trustworthy at scale.
“Our POC worked on ten documents, then broke on ten thousand.”
The demo-to-production gap — engineered away, not wished away.
“We can’t trust the numbers the AI extracts.”
Verification, provenance, and validation for structured output you actually have to act on.
“Our LLM system is slow or wrong and no one knows why.”
Usually it’s the data pipeline underneath — not the model, and not the prompt.
“We’re about to spend six figures on AI — is it real?”
Independent technical due diligence before the budget is committed: feasibility, architectural risk, and the honest path to production.
“This data is sensitive or regulated and can’t leak.”
Multi-tenant isolation, access control, prompt-injection defense, and audit-ready security.
Full-Scope Engagement (Idea → Production)
End-to-end: strategy, architecture, and hands-on build — from first idea to a system that holds up in production.
For high-stakes systems where correctness and reliability are critical.
POC → Production Accelerator
Take an early concept, POC, or MVP and turn it into a secure, observable, scalable production system.
For startups and product teams moving fast but needing senior oversight.
Fractional AI & Data Architect
Ongoing strategic and technical leadership — roughly 1–3 days a week — without hiring full-time. Architecture, reviews, implementation guidance, and team mentorship.
Best for teams with continuous AI or data initiatives.
AI Security & Trust Audit (Fixed-Scope)
A defined review of an AI system’s security, data isolation, and failure modes — with prioritized findings and a remediation path.
For regulated or sensitive-data deployments.
Architecture Review & Roadmap (Short Engagement)
A deep technical assessment of your current system, prototype, or idea — with clear recommendations, risk analysis, and a step-by-step path to production.
Ideal for teams that need clarity before investing further.
Executive & CTO Advisory
High-level guidance on AI strategy, technical direction, vendor/security evaluation, and long-term architectural decisions.
Ideal for organisations making significant AI investments.
For the same leadership-development AI platform I built the production infrastructure for (AI Book Companion Platform with Enterprise Security and Observability), I designed and …
For one of the largest privately held companies in the US, I engineered the platform infrastructure for a conversational AI book companion — a tool that helps readers learn and …
For a sports media technology company, I designed and built a production AI pipeline that extracts compelling game narratives from live broadcast transcriptions. The system …
Building on my initial EV charger site selection model, I redesigned the platform from a single-model kWh predictor into a hybrid scoring system that combines LightGBM demand …
For an energy infrastructure company evaluating locations for EV charger installation, I developed a geospatial machine learning pipeline integrating real charging network data, EV …
As technical lead and AI architect for a civil engineering firm, I designed and built an end-to-end technical report generation system combining multi-source document ingestion, …
