Member of Technical Staff - Post-Training; Reinforcement Learning & Generalization

Employer-published remote role. Listed location(s):
Europe;
New York;
Toronto. Remote does not imply worldwide eligibility. Check the original listing for residency, work authorization, time zone, language and travel requirements.

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!

Key Overview:

As a Member of Technical Staff in Post-Training, you will train our large language models (LLMs) with reinforcement learning and develop methods that help them generalize beyond the distribution they were trained on. You will design the training recipes, environments, and evaluations that tell us whether a model has truly learned a skill or has only fitted its training tasks, and turn what works into the recipes behind our production models.

You will work closely with the post-training data infrastructure, evaluation, and pre-training teams.

Key Responsibilities

• Design, run, and analyse large-scale RL post-training experiments (e.g., RLHF, RL from verifiable rewards).
• Research and develop methods that improve out-of-distribution generalization, such as reward design, environment and task diversity, curricula, and regularization.
• Build held-out evaluations that measure generalization to unseen tasks, domains, and formats, and that catch reward hacking and benchmark overfitting.
• Diagnose training dynamics and failure modes, including instability, reward over-optimization, and capability regressions.
• Turn successful research into robust, reproducible training recipes for production models.

Qualifications

• Strong research and software engineering skills, with hands-on experience training LLMs.
• Experience applying reinforcement learning to LLMs (e.g., PPO, GRPO, RLHF, RLVR), ideally at scale.
• Track record of work on generalization, robustness, or distribution shift, through publications or shipped models.
• Rigorous experimental practice: clean ablations, careful controls, and sound conclusions from noisy results.
• Experience with distributed training (e.g., JAX, PyTorch, FSDP, Megatron) is a plus.
• Excellent communication skills.
• Deep understanding of data quality principles and best practices: demonstrates willingness to dive deep into data while possessing strong intuition for assessing the quality of datasets and anticipating how different data characteristics will impact model training outcomes.

Working Location

This role can be based remotely or from one of our office locations listed on the job description - there is no minimum in-office qualification requirement. We care most about hiring exceptional people regardless of locations, though please check the location listed on the posting for guidance around the core time zone or working hours alignment expected for the role.

• A weekly lunch stipend of $75/£75 or equivalent in your local currency for lunch.
• Full health and dental benefits, including a separate budget for mental health.
• RRSP matching, 401K, Pension Scheme.
• 100% Parental…