About
Hey there! I am a Machine Learning Researcher at JetBrains, working on software-engineering agents and the tooling they need to collaborate effectively with developers and teams. I studied computer science at the Technical University of Munich, where I completed my master’s degree with distinction in November 2025.
My work is broadly centered on software engineering agents (for code and beyond) that robustly solve tasks over long horizons, and adapt continually from experience. I am particularly interested in how we can make such agents efficient and effective—in terms of context management, memory, and compute—so that they are capable of robustly operating in complex real-world computer systems and remain accessible to a wide range of users and organizations.
My path into research was shaped by years of work as a full-stack engineer in long-term internships and data science roles. This foundation gives me both the technical depth to build robust research infrastructure and an intuitive understanding of the developer workflows and pain points that drive my research questions. It also taught me to communicate complex technical ideas across disciplines—bridging the gap between rigorous ML research and practical engineering challenges.
If my research interests or projects resonate with you, feel free to reach out or explore my projects and writing below.
- View selected work on the projects page.
- Read my notes and write-ups on the blog.
Latest updates
Completed my master’s degree in computer science at the Technical University of Munich with distinction.
The Complexity Trap was accepted to the Fourth Workshop on Deep Learning for Code (DL4C) at NeurIPS 2025. We show that simple observation masking is as efficient as LLM summarization for agent context management and introduce a novel context management strategy that reduces costs by up to 11% compared to these baselines.
GitGoodBench was accepted to the First Workshop for Research on Agent Language Models (REALM) at ACL 2025. We introduce a novel benchmark for evaluating AI agent performance on Git operations, establishing a 21% baseline with GPT-4o.
CTIM-Rover was accepted to the First Workshop for Research on Agent Language Models (REALM) at ACL 2025. We investigate episodic memory in SE agents, finding that retrieval noise can degrade performance compared to stateless baselines.
Started a full-time position as Machine Learning Researcher at JetBrains in the AI agents team.