Member of Technical Staff - RL Environments (Fully Remote)

• Building AI agents that can assist with any kind of enterprise work is a challenging, open-ended problem.
• Replicating real work environments as realistically as possible with hard tasks, plausible input data, and clear rewards.
• You will create these RL environments, run agents inside them, and improve both.

Key Responsibilities:

• Build new RL environments targeting different agentic capabilities and industry areas.
• Train and evaluate agents in those environments.
• Work with external vendors and build tools for high-quality task, data, and verifier quality.

Qualifications:

• Engineered agents and optimized them for specific industry use cases.
• Experience reviewing agent trajectories and tuning reward designs.
• Built synthetic data pipelines and designed annotation workflows.
• 6 weeks of paid vacation, health/dental benefits, and parental leave top-up.
• Annual enrichment benefits and education stipend.
• Home office stipend and co-working benefit.

Cohere

Cohere is a security-first enterprise AI company building cutting-edge foundation models and end-to-end products. It is a global team of researchers, engineers, and designers headquartered in Toronto with offices worldwide.