AI Engineer & Tech Lead

Scroll
ENTERPRISE AI, IN PRODUCTION

MULTI-AGENT
ORCHESTRATION

As Tech Lead on ŠkoPilot at Škoda Auto, I architect and ship an enterprise multi-agent assistant serving 30,000+ internal users — owning the design and writing the code, not just directing it.

  • Multi-agent orchestration with tool/function-calling & MCP
  • Forked & extended Google ADK with custom agent flows & typed streaming
  • LLM evaluation frameworks — golden datasets & regression benchmarks
  • Production RAG platform with document-parsing pipelines
0 ŠkoPilot Users
1M+ Player Sessions
0 Anomalies / Mo Automated
FUNCTIONS FRONTEND REST API DATABASE AI AGENT
SKILL MAP

EXPERTISE
MATRIX

Five years of hands-on engineering across AI, backend and architecture — with the last 1.5 leading production AI at enterprise scale. Measured, not claimed.

  • AI Engineering — Multi-Agent Orchestration, Google ADK, MCP, LangChain
  • Evaluation — Eval/Benchmarking Frameworks, Regression Testing
  • Architecture — Reference Patterns, Reusable Platforms, System Design
  • Backend — Python, Node.js, C# /.NET, Kotlin/JVM
  • Cloud — Azure OpenAI, GCP, Docker, Event-Driven

Mission Control

The technology behind the intelligence
// 01

AI & Orchestration

Multi-agent systems with tool/function-calling, MCP integrations, and context management across multiple model providers — built on a forked, extended Google ADK.

Azure OpenAIPython Google ADKMCPGeminiLangChain
// 02

Evaluation & Quality

Long-lived eval frameworks that track LLM output quality over months, not just at launch — plus production RAG with document-parsing and contextual memory.

EvalsRegression Testing Golden DatasetsRAG
// 03

Systems & Backend

Solid, maintainable foundations — from event-driven backends to high-concurrency JVM platforms serving over a million sessions. Built to scale and to last.

C# /.NETKotlin/JVM Node.jsDockerSQL / NoSQL
LIVE DEMO

WATCH IT WORK

agent — bash
DEEP DIVES

CASE
STUDIES

All case studies →

Long-form system and platform designs for production AI. Each one states its assumptions up front, argues the trade-offs, and commits to a decision — because the reasoning is the deliverable, not just the conclusion.

// 01 Platform Design · Regulated Gaming

Enterprise Agentic Automation Platform

One multi-use-case agent platform, the seven-phase lifecycle that governs it, and the argument for which use case to build first. Buy the runtime, build the governance.

Google ADKVertex AI MCPA2AHuman-in-the-loopGovernance
Read case study →~14 min
// 02 System Design · Streaming

Conversational AI Assistant for Search

Grounded Czech intent-to-catalog mapping as strict structured output, at 1.2M conversations a day inside a 5–10 s p99 budget — where the schema, not the prompt, makes hallucination impossible.

Hybrid RAGpgvector Structured OutputsFastAPIRedisEvals
Read case study →~10 min
Let's Talk

Building the next thing
in enterprise AI?

Agentic systems, evals, AI-native developer tooling. Open to lead & architect-level conversations — always up for a good one.

Get In Touch