Member of Technical Staff in Post-Training (LLM/RL)

Location: Remote or from offices in Europe, New York, or Toronto; no minimum in-office requirement, with core time zone and working-hours alignment expected based on the listed location.

Salary: Canada — Toronto and Montreal: CA$295K–CA$535K base salary; USA — New York, California, and Washington: $205K–$380K base salary; other US states: $175K–$325K base salary. Equity is offered.

Company

Cohere builds security-first enterprise AI models and end-to-end products for real-world business applications.

What you will do

• Design, run, and analyze large-scale reinforcement learning post-training experiments, including RLHF and reinforcement learning from verifiable rewards.
• Research methods for improving out-of-distribution generalization through reward design, diverse environments and tasks, curricula, and regularization.
• Build held-out evaluations for unseen tasks, domains, and formats while detecting reward hacking and benchmark overfitting.
• Diagnose training dynamics and failure modes such as instability, reward over-optimization, and capability regressions.
• Convert successful research into robust, reproducible training recipes for production models.
• Collaborate with post-training data infrastructure, evaluation, and pre-training teams.

Requirements

• Strong research and software engineering skills with hands-on experience training large language models.
• Experience applying reinforcement learning to LLMs, such as PPO, GRPO, RLHF, or RLVR, ideally at scale.
• Research or shipped-model experience in generalization, robustness, or distribution shift.
• Rigorous experimental practice, including clean ablations, careful controls, and sound conclusions from noisy results.
• Excellent communication skills and a deep understanding of data quality and dataset impact on model training.

Nice to have

• Experience with distributed training technologies such as JAX, PyTorch, FSDP, or Megatron.

Culture & Benefits

• Remote-friendly work with offices in Toronto, London, New York City, San Francisco, Montreal, Paris, Berlin, and Seoul.
• Weekly lunch stipend of $75, £75, or equivalent in local currency.
• Health and dental benefits, mental health budget, RRSP matching, 401K, and pension scheme.
• Six weeks of paid vacation, parental leave top-up for up to six months, and annual enrichment benefits.
• Education and learning stipend, coworking benefit, home office stipend, and travel budget for remote employees.
• Annual company offsite and office-based lunch, social, and community programs.