Member of Technical Staff - RL Environments
CohereRemotely
automationreinforcement learningagentsrl environmentsannotation workflowssynthetic data pipelines
Job Description
📋 Description
- Role creating RL environments and running AI agents inside them.
- Improve agents and environments; loop with customer feedback.
- Collaborate across modeling and product to close gaps in agent performance.
- Work with external vendors to build high-quality RL environments and tools.
- Automate discovery of model capability gaps and measure performance during evals and training.
🎯 Requirements
- Experience engineering agents and optimizing for industry use cases.
- Ability to review agent trajectories to identify failure points and improve via training or harness
- Strong focus on measuring agentic capabilities and turning data into repeatable processes.
- Experience with verifier implementations and reward design discussions.
- Experience designing and running annotation workflows to surface insights and verify data quality.
- Experience building synthetic data pipelines to scale eval and training; familiarity with hands-on
🎁 Benefits
- Remote-friendly with office options in multiple cities; support for remote work and relocation as
- Competitive compensation and benefits package; health and dental coverage.
- Parental leave, retirement plans, and ongoing education stipends.
- Paid vacation and travel budget for remote/offsite collaboration.
- Home office stipend to set up a productive workspace.