Remote AI Agent Environments Engineer

AI Chopping Block; Greater London; Hybrid; GBP 110,000 - 170,000; Full time

Benefits offered by this job

Lunch stipend

Health and dental benefits

RRSP matching

Parental leave

Enrichment benefits

Paid vacation

Travel budget

Home office stipend

Job summary

Cohere is seeking an experienced engineer to create RL environments and run agents for enterprise tasks. You will design diverse environments, train agents, and iterate to improve both agents and environments.

You will collaborate with modeling and product teams, external vendors, and customers, contributing to scalable evaluation loops and robust data pipelines. Remote-friendly role with office options.

Qualifications

• Experience engineering agents for industry use cases.
• Experience reviewing agent trajectories to identify failures and improve via training or harness engineering.
• Ability to measure agent capabilities and turn that into repeatable processes.
• Experience with verifier implementations and reward design.
• Experience designing and running annotation workflows to surface insights.
• Experience building synthetic data pipelines to scale eval and training.

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.
• Collaborate with external vendors to create high-quality RL environments and build tools to ensure quality.
• Automate discovery of model capability gaps and measure performance during evals and training.

Skills

Agent engineering

RL optimization

Verifier design

Annotation workflows

Synthetic data

Education

Bachelor's degree in CS/ML

Tools

Python

RL frameworks

Job description

Cohere is seeking an experienced engineer to create RL environments and run agents for enterprise tasks. You will design diverse environments, train agents, and iterate to improve both agents and environments.

You will collaborate with modeling and product teams, external vendors, and customers, contributing to scalable evaluation loops and robust data pipelines. Remote-friendly role with office options.