Latest AI JobsBrowse Jobs
Cohere logo

Member of Technical Staff - RL Environments

CohereLondonModeling
Apply on company site
Salary
$250K - $535K CAD
Job type
Full-time
Work mode
Remote
Posted
17 Aug 2026
Status
Open · checked 7d ago

About this role

This is a full-time Member of Technical Staff position focusing on reinforcement learning environments at Cohere, available to candidates working remotely or from the London office. This role suits technical professionals who want to build, test, and improve realistic work environments and AI agents for enterprise business challenges.

Role Overview

Solving complex enterprise work through AI agents requires replicating real-world work environments with high accuracy. In this position, the professional creates these reinforcement learning environments, deploys AI agents within them, and refines both the agents and the settings. The work directly influences customer solutions by establishing tasks, input data, and clear reward systems.

Key Responsibilities

Build novel reinforcement learning environments designed for specific industry areas and agentic capabilities.
Train and evaluate artificial intelligence agents inside the created environments.
Integrate all components, including tasks, data, tool implementations, and verifiers.
Bridge modeling and product teams to identify performance gaps and enhance agent and environment quality.
Partner with external vendors to produce high-standard reinforcement learning environments and build tools for data and verifier quality.
Automate the discovery of model capability gaps and measure agent performance throughout training and evaluations.

Requirements

Experience engineering AI agents and optimizing them for specific industry use cases.
Demonstrated ability reviewing agent trajectories to find failure points and correct them using model training or harness engineering.
Passion for measuring agentic capabilities and turning that process into a repeatable system.
Experience designing verifier implementations and tuning reward designs based on expected outcomes.
Background designing and running annotation workflows to check data quality and surface performance insights.
Experience building synthetic data pipelines to scale training and evaluation efforts.

Nice to Have

Practical experience training with reinforcement learning, including scaling, troubleshooting, and tuning environments.

Skills and Tools

Reinforcement learning environments and agent training
Synthetic data pipeline creation
Annotation workflow design
Verifier implementation and reward design
Harness engineering and trajectory review

Salary and Benefits

Salary range between $250,000 and $535,000 CAD per year.
Weekly lunch stipend of $75/£75 or equivalent local currency.
Full health and dental benefits alongside a separate mental health budget.
Retirement plans including RRSP matching, 401K, and Pension Scheme.
100% parental leave top-up for up to 6 months for either parent.
Annual enrichment benefits covering fitness, wellness, arts, culture, and workspace improvements, plus an education and learning stipend.
Six weeks of paid vacation, equating to 30 working days.
Travel budget for visiting other offices and attending the annual company offsite.
Home office setup stipend of $500 or a co-working benefit for remote workers.

About the Company

Cohere is a security-first enterprise artificial intelligence company building cutting-edge foundation models and end-to-end products to solve real-world problems. Headquartered in Toronto with key international offices, the company brings together researchers, engineers, and designers dedicated to expanding model capabilities for enterprise adoption.

How to Apply

Interested candidates should submit their application directly through the official Cohere careers page.

Questions candidates ask

What is the salary for the Member of Technical Staff - RL Environments role?

The salary ranges from $250,000 to $535,000 CAD per year.

Can I work remotely for this position?

Yes, this role can be based remotely or from one of the company's office locations, though candidates should check core time zone expectations for the position.

What vacation time is provided for full-time employees?

Full-time employees receive 6 weeks of paid vacation, which equals 30 working days.

Where is Cohere headquartered?

Cohere is headquartered in Toronto with key offices in London, New York City, San Francisco, Montreal, Paris, Berlin, and Seoul.

How should I apply for this job?

Applications should be submitted directly through the official Cohere careers page.

Ready to apply?

The application is on the official Cohere careers page.

Apply on company site