Krakow, Poland, 17 - 19 June 2026
Software engineer with a strong backend foundation and a steadily growing specialization in artificial intelligence. Professionally connected with the world of Java and distributed systems, where for years he has been designing and developing microservices, APIs, and platforms running in cloud-native and containerized environments.
Currently serving as an AI Technical Lead at j-labs, focusing on the exploration and practical application of AI technologies — from traditional backend systems to modern LLM-based solutions. He combines engineering precision with an analytical approach to problem-solving, always balancing complexity, maintainability, and real business value.
Graduate of postgraduate studies in Machine Learning and Data Science at AGH University of Science and Technology, with hands-on experience in deep learning, NLP, and data analysis. Particularly interested in AI agents, RAG systems, and the practical use of artificial intelligence in production environments — with a strong focus on identifying where AI genuinely adds value and where it merely increases complexity.
An engineer who prefers demonstrating the real capabilities and limitations of AI over promising “AI magic.” If you want to understand how to combine classical software engineering practices with the new wave of LLM-based tools, you’re in the right place.
Detailed description
AI agents for SRE are moving from experiments to production, but reliability, observability, and safety are still major challenges. In this session, we present our autonomous SRE diagnosis agent built with Microsoft Agent Framework, Magentic orchestration, Memgraph, k8s, OpenSearch, and OpenTelemetry.
We explain why we chose graph-based orchestration for long-running diagnostic workflows and share practical lessons from building the system: controlling context explosion, parallelizing investigative agents, enforcing structured outputs, and deduplicating noisy alerts. We also show how graph databases enables operational memory by correlating incidents and reusing past diagnostic insights.
Finally, we discuss safety boundaries for autonomous operations and the challenge of evaluating non-deterministic AI-driven SRE systems using ITBench and internal experiments.
Takeaways
- Tradeoffs between Pregel, A2A, and event-driven agent architectures.
- Why orchestration matters more than raw model reasoning.
- Practical techniques for avoiding context explosion in observability systems.
- Using Memgraph to correlate similar incidents and reuse operational knowledge.
- Magentic-One as an alternative to Group Chat and ReACT
- Safety and auditability patterns for autonomous SRE agents.
Target audience
- SREs and DevOps Engineers
- AI Engineers
- Architects designing autonomous operational tooling
- Engineering leaders evaluating AI for production infrastructure
Searching for speaker images...
Ticket prices will go up in...
You missed out!
Venue address
ICE Krakow, ul. Marii Konopnickiej 17
Phone
+48 691 793 877
info@devoxx.pl