Remote RL Environments Engineer

Cohere; Greater London; Hybrid; GBP 70,000 - 120,000; Full time

Benefits offered by this job

Weekly lunch stipend

Full health and dental benefits

RRSP matching / Pension

Parental Leave top-up

Enrichment benefits

Learning stipend for conferences

Vacation 6 weeks

Office/remote work flexibility

Home office stipend

Job summary

Cohere is seeking engineers to build RL environments for enterprise tasks, run AI agents inside them, and improve both agents and environments. You will influence real-world outcomes by designing challenging tasks, crafting input data, and defining rewards for correct behavior.

You will leverage your experience in agent evaluation, annotation workflows, and synthetic data pipelines to scale evaluation and training. Remote-friendly role with strong collaboration across modeling and product teams.

Qualifications

• Experience engineering agents for industry use cases.
• Ability to review agent trajectories and fix failures with model training or harness engineering.
• Focus on measuring agentic capabilities and turning this into repeatable processes.
• Experience translating desired agent outcomes into verifier implementations and reward designs.
• Experience designing and running annotation workflows to surface insights into agent performance.

Responsibilities

• Build new RL environments targeting different agentic capabilities and industry areas
• Train and evaluate agents in those environments
• Make all 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

Skills

Agent engineering

Agent evaluation

Annotation workflows

Synthetic data pipelines

RL training and tuning

Job description

Cohere is seeking engineers to build RL environments for enterprise tasks, run AI agents inside them, and improve both agents and environments. You will influence real-world outcomes by designing challenging tasks, crafting input data, and defining rewards for correct behavior.

You will leverage your experience in agent evaluation, annotation workflows, and synthetic data pipelines to scale evaluation and training. Remote-friendly role with strong collaboration across modeling and product teams.