Member of Technical Staff - Post-Training (Reinforcement Learning & Generalization) is open at Cohere in Europe (remote). The posting gives a salary of CA$295K - CA$535K. Posted on Oct 14, 2026, and still on Cohere’s careers page when we last checked, on Nov 14, 2026.
About the role
Design, run, and analyse large-scale RL post-training experiments (e.g., RLHF, RL from verifiable rewards). - Research and develop methods that improve out-of-distribution generalization, such as reward design, environment and task diversity, curricula, and regularization. - Build held-out evaluations that measure generalization to unseen tasks, domains, and formats, and that catch reward hacking and benchmark…
The opening lines of the posting. The rest is on Cohere’s careers page.
Hiring at Cohere
Cohere has 121 open roles right now, 79 of them remote. Most are in Engineering, Sales & Business Development and Marketing & Community. The median advertised salary across its roles with a published range is $250K. See all its roles
Similar Engineering jobs
All Engineering jobs- Senior/Staff Software Engineer, Developer ExperienceCohere · 🇬🇧London$185K - $300KLead and abovePythonTypeScriptDocker
- Software Engineer - Data Center ToolingLambda · 🇺🇸San Francisco Office (Fremont St)$230K - $340KGoPythonReact
- IT Operations EngineerPhysical Intelligence · 🇺🇸San Francisco—PythonLinuxBash
