Poolside28.04.2026

Member of Engineering (Reinforcement Learning)

Полная занятостьУдалёнка

Обязанности

01Research and experiment on ways to improve reasoning and code generation for LLMs
02Own the full experiment life cycle from idea to experimentation and integration
03Keep up with the latest research, and be familiar with the state of the art in LLMs, RL, and code generation
04Translate research ideas into clean, reusable codebases that other researchers can build on
05Design, analyze, and iterate on data generation and training of LLMs
06Implement and iterate on RL training pipelines that scale reliably across domains
07Diagnose training instabilities and failures, debug RL runs and propose mitigation methods
08Write high-quality, reproducible and maintainable code

01Experience with Large Language Models (LLM), including: Understanding of the Transformer architecture and scaling laws, Mid-training and post-training techniques, Experience training reasoning and/or agentic models, Hands-on use of LLMs, with a sense of their capabilities and limitations
02Reinforcement Learning experience: Solid grasp of Reinforcement Learning concepts and familiarity with modern algorithms, Experience developing distributed, large-scale RL pipelines from data creation to evaluations
03Research experience: Scientific publications in any of the following topics: Reinforcement Learning, LLMs and reasoning models, Ability to discuss the latest research with sufficient level of detail, Is reasonably opinionated
04Engineering skills: Strong machine learning, algorithm skills and engineering background, Experience with distributed training, Excellent programming skills in Python, Familiarity with a deep learning framework (Pytorch or JAX)