I am interested in the practical stack behind RL for LLMs: rollout generation, reward signals, policy optimization, evaluation, and debugging. I have been exploring open-source RL-for-LLM tooling including rLLM, with an eye toward making post-training more understandable and reproducible.
A judge-driven multi-agent retrieval system for financial document QA. The system decomposes answering into retrieval, reasoning, and judging agents, then uses feedback-driven retries to recover from weak answers. I see this as a bridge between retrieval systems and RL-style improvement loops: feedback, credit assignment, and iterative correction.
A learning repo for inference engineering: serving, evaluation, model behavior, and the operational details that matter once model systems move from notebooks into real environments.