Ir para o conteúdo
AI.info

jobs

Member of Technical Staff - Post-Training (Reinforcement Learning & Generalization)

Who are we? Cohere is the leading security-first enterprise AI company. We build cutting-edge foundation AI models and end-to-end products that are designed to solve real-world business problems.

Em inglês

Company
Cohere
Location
Europe; New York; Toronto
Status
Open
Posted
2026-10-14 10:10 UTC

Cohere is hiring a Member of Technical Staff for post-training to train its large language models with reinforcement learning and to develop methods that help them generalize beyond their training distribution. The work covers designing large-scale RL experiments such as RLHF and RL from verifiable rewards, reward design, curricula and regularization, and held-out evaluations that catch reward hacking and benchmark overfitting, then turning results into production training recipes. The posting asks for hands-on LLM training, applied RL experience, and rigorous experimental practice. The role can be fully remote.

Original job posting