Remote RL Environments Engineer for Enterprise AI

Cohere; City Of London; A distancia; GBP 100.000 - 150.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Lunch stipend; health benefits; remote

Parental leave

Enrichment benefits

Education stipend

Vacation bonus

Travel to other offices

Home office stipend

Descripción de la vacante

Cohere is hiring for a role that builds and refines reinforcement learning environments and AI agents for enterprise use. You will create challenging tasks, run agents, and improve both agents and environments based on feedback from real customers.

You will iterate on tasks, data, tool implementations, and verifiers, collaborating with modeling and product teams to close performance gaps. Remote-friendly with global office presence.

Formación

• You have engineered agents and optimized them for specific industry use cases.
• You have spent dozens of hours reviewing agent trajectories to pinpoint exact failure points and fix them with model training or harness engineering.
• You obsess over measuring agentic capabilities and turning that into a repeatable process.
• You have had many debates about what a good outcome from an AI agent should look like, you translated that into verifier implementations and tuned the reward designs.
• You have designed and run annotation workflows to surface insights into agent performance and verify data quality.
• You have built synthetic data pipelines to scale eval and training efforts.
• You use agents yourself in your daily work, and have stories about how you improved your setup to 10x your productivity.
• A plus: you have experience with training with RL: scaling, troubleshooting and tuning the environments.

Responsabilidades

• Build new RL environments targeting different agentic capabilities and industry areas.
• Train and evaluate agents in those environments.
• Make all the pieces work together: tasks, data, tool implementations, and verifiers.
• Work across modeling and product to identify gaps in agent performance, and improve both the agents and the environments.
• Work with external vendors to create high-quality, expert-built RL environments, and build tools to ensure high task, data, and verifier quality.
• Automate the discovery of model capability gaps, and systematically measure agent performance during evals and training.

Descripción del empleo

Cohere is hiring for a role that builds and refines reinforcement learning environments and AI agents for enterprise use. You will create challenging tasks, run agents, and improve both agents and environments based on feedback from real customers.

You will iterate on tasks, data, tool implementations, and verifiers, collaborating with modeling and product teams to close performance gaps. Remote-friendly with global office presence.