Poolside28.04.2026

Member of Engineering (Reinforcement Learning Infrastructure)

Полная занятостьУдалёнка

Обязанности

01Keep up with the latest research and stay familiar with the state of the art in LLMs, RL, and code generation
02Develop methods for tuning training and inference end-to-end for high throughput
03Design data control systems in an RL pipeline that govern what the model sees and when
04Debug cases where infrastructure decisions are silently degrading learning dynamics
05Build observability tooling that surfaces system-level issues causing training regressions
06Help build robust, flexible and scalable RL pipelines
07Optimize performance across the stack – networking, memory, compute scheduling, and I/O
08Write high-quality, pragmatic code
09Collaborate with the team to plan future steps, discuss progress, and stay in touch

01Experience with large language models and model post‑training workflows
02Understanding of reinforcement learning principles and main bottlenecks
03Solid software engineering fundamentals including testing, code review, and debugging complex systems
04Proficiency in Python with concurrency, asynchronous programming, multiprocessing and performance optimization
05Familiarity with deep learning frameworks such as PyTorch or JAX and RL workflows (rollouts, replay buffers, policy updates)
06Experience designing and maintaining distributed RL training systems
07Experience with large‑scale LLM training infrastructure
08Experience with profiling tools across the stack (e.g., py‑spy)
09Experience with inference stacks (e.g., vLLM)
10Nice to have: open‑source contributions to RL or distributed ML projects