Staff AI Agent Engineer — Remote RL Environments

Member of Technical Staff - RL Environments; Greater London; Remoto; GBP 70.000 - 110.000; Tempo pieno

Vantaggi offerti da questo lavoro

Weekly lunch stipend

Health and dental benefits

RRSP matching / Pension

Parental Leave top-up

Learning stipend

Vacation (6 weeks)

Home office stipend

Descrizione del lavoro

Cohere is hiring for a role focused on building and evaluating reinforcement learning environments that mirror real enterprise work. You will run AI agents within these environments, optimize both agents and environments, and incorporate feedback from customers to continuously improve the loop.

The position involves collaborating with modeling and product teams to identify gaps, working with external vendors for high-quality environments, and developing tools to ensure data and task quality.

Competenze

• Engineered agents and optimized them for enterprise RL use cases.
• Reviewed agent trajectories to identify failure points and improve through training or harness engineering.
• Measured agentic capabilities and translated results into verifier implementations and reward designs.
• Designed and ran annotation workflows to surface insights into agent performance and data quality.
• Built synthetic data pipelines to scale evaluation and training workflows.

Mansioni

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

Conoscenze

RL environments

Agent training

Experimentation

Verification tools

Synthetic data pipelines

Annotation workflows

Hardware-neutral testing

Daily collaboration

Strumenti

RL frameworks

Python

Descrizione del lavoro

Cohere is hiring for a role focused on building and evaluating reinforcement learning environments that mirror real enterprise work. You will run AI agents within these environments, optimize both agents and environments, and incorporate feedback from customers to continuously improve the loop.

The position involves collaborating with modeling and product teams to identify gaps, working with external vendors for high-quality environments, and developing tools to ensure data and task quality.