Member of Engineering (Reinforcement Learning Infrastructure)
Skills
Software DevelopmentConcurrent ProgrammingDistributed SystemsEngineeringProgrammingPythonReinforcement Learning
What the job involves
The main requirements, responsibilities and hiring steps.
Requirements
- Experience with LLMs and model post-training workflows
- Understanding of Reinforcement Learning and its main bottlenecks
- Solid software engineering fundamentals including testing code review and debugging complex systems
- Proficiency in Python with concurrency asynchronous programming multiprocessing and performance optimization
- Familiarity with PyTorch or JAX and RL workflows such as rollouts replay buffers and policy updates
- Experience designing and maintaining distributed RL training systems
- Experience with large-scale LLM training infrastructure
- Experience with profiling tools across the stack such as py-spy
- Experience with inference stacks such as vLLM
Nice to have
- Open-source contributions to RL projects
- Open-source contributions to distributed ML projects
Day to day
- Build and scale infrastructure for reliable and efficient frontier RL training of Large Language Models
- Research and develop new exploration and training algorithms while designing and scaling RL environments
- Implement end-to-end solutions across the stack and optimize performance across networking memory compute scheduling and I/O
Hiring process
- Intro call with one of our Founding Engineers
- Technical Interview(s) with one of our Founding Engineers
- Team fit call with the People team
- Final interview with one of our Founding Engineers