Tech Stack

Description

You will collaborate with researchers and engineers to advance RL for large language models, architecting training infrastructure and implementing novel methods to improve agent capabilities, reasoning, and safety.

Requirements

• Proficient in Python and async/concurrent programming (e.g., Trio)
• Experience with ML frameworks (PyTorch, TensorFlow, JAX)
• Industry experience in ML research
• Strong systems design and communication skills
• Passionate about AI safety and beneficial systems

Responsibilities

• Architect and optimize core RL infrastructure across GPU clusters
• Design and implement novel training environments and evaluations for RL agents
• Drive performance improvements through profiling and optimization
• Implement caching solutions and debug distributed systems
• Develop automated testing frameworks and scalable APIs