About

I'm an AI Systems Performance Engineer on the Red Hat PSAP team, working at the intersection of distributed systems, AI inference, and open source. My background is a bit unconventional: Bachelor's in Electronics and Automation Engineering from ULPGC, a Master's in Biomedical Engineering at Vilnius Tech, and research in hyperspectral imaging and computer vision — before landing where I actually belong: digging into how complex distributed AI systems work and pushing them to their limits.

What I do

At Red Hat I contribute to making AI systems faster, more scalable, and more resource-efficient. A lot of that work lives in the vLLM and llm-d ecosystems — tracing performance bottlenecks in distributed inference setups, understanding why a model runs twice as slow on paper-identical hardware, and helping teams get more out of the infrastructure they already have.

I care about understanding how and why things work, not just that they do. That's the thread connecting everything from my early research days to what I ship now.

Background

My path ran through university research at VGTU, DevOps and infrastructure engineering, and deep learning infrastructure, each role sharpening a different part of how I think about systems. I believe continuous learning is the minimum requirement for doing good work in any technical field — and there's no better way to keep learning than working on genuinely hard problems.

When I'm not deep in a performance trace, I'm exploring new places, throwing weights around at the gym, or swimming. Architecture and design thinking get me genuinely excited too.