Member of Technical Staff - Post-Training (Reinforcement Learning & Generalization)
Toronto, ON295k–535k $/anTélétravailTemps plein
Cohere: Cohere is the leading security-first enterprise AI company.
Candidates need strong research and software engineering skills, hands-on experience training LLMs, and experience applying reinforcement learning to LLMs. A record of work on generalization, robustness or distribution shift, and rigorous experimental practice are also required.
JAX, PyTorch, FSDP, Megatron