Machine Learning Systems Engineer, RL Engineering

Build, maintain, and improve the algorithms and systems used to train AI models (e.g., Claude) on reinforcement learning data (RLHF and related methods). Focus on speed, reliability, and usability of reinforcement learning training pipelines and tooling to accelerate research progress. Collaborate with finetuning researchers, contribute to scalable infrastructure, profiling and optimizing training workflows, and implementing new training algorithms for production and research models. Strong emphasis on solving practical system-level problems, improving developer productivity, and supporting a research team working on large-scale ML systems.