Cohere

Research internship focused on combining self-distillation and reinforcement learning for LLMs, with applications to code generation and agentic tasks. Investigates mechanisms for handling extremely large rollouts in RLVR to advance state-of-the-art in LLM training.

Cohere is hiring a Member of Technical Staff for their Integration/RL Team, focusing on developing and scaling machine learning algorithms and infrastructure for LLM post-training, particularly large-scale, distributed RL methods. The role involves enhancing the post-training codebase, implementing new research tools, optimizing algorithms, and scaling distributed RL.