Member of Technical Staff - RL Environments

Cohere; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

Cohere is building advanced reinforcement learning environments and agents for enterprise AI applications. In this role, you will create RL environments, run agents, and improve both agents and environments through iterative training and evaluation.

You will collaborate with modeling and product teams to close gaps in performance and work with external vendors to ensure high-quality data, tasks, and verifiers.

Qualifications

• Experience engineering agents for industry use cases.
• Experience reviewing agent trajectories to pinpoint failure points.
• Experience measuring agentic capabilities and improving through training.

Responsibilities

• Build new RL environments targeting different agentic capabilities and industry areas.
• Train and evaluate agents in those environments.
• Assemble tasks, data, tool implementations, and verifiers to run end-to-end.
• Collaborate across modeling and product to identify gaps in agent performance.
• Work with external vendors to create high-quality RL environments and tools.
• Automate discovery of model capability gaps and measure performance during evals.

Skills

Agent engineering

RL environments

Agent evaluation

Job description

Who are we?

Cohere is the leading security-first enterprise AI company. We build cutting-edge foundation AI models and end-to-end products that are designed to solve real-world business problems.We’re training and deploying frontier models for enterprises who are building AI systems. We believe that our work is instrumental to the widespread adoption of AI and we are looking for folks that want to be part of that.We obsess over what we build. Each one of us is responsible for contributing to increasing the capabilities of our models and the value they drive for our customers. Cohere is a team of researchers, engineers, designers, and more, who are all passionate about their craft.We are a global technology company headquartered in Toronto with key offices in London, New York City, San Francisco, Montreal, Paris, Berlin and Seoul. Join us!

Role Overview:

Building AI agents that can assist with any kind of enterprise work is a challenging, open-ended problem. One key piece of solving it is replicating real work environments as realistically as possible - filling them with hard tasks to solve, creating plausible input data, and defining clear rewards for completing the work the right way. We build many of these reinforcement learning (RL) environments, then drop our agents into them to evaluate or train them. In this role, you are responsible for creating these RL environments, running AI agents inside them, and improving both the agents and the environments in the process. The results reach customers, whose feedback feeds back in - and the agent/environment improvement loop continues.

Key Responsibilities:

There are many open problems in this space. As a Member of Technical Staff, RL Environments, you will:

• 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

Qualifications:

You may be a good fit if:

• 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
...}