Requirements

• Strong research and software engineering skills, with hands-on experience training large language models (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.
• Excellent communication skills.
• Deep understanding of data quality principles and best practices with the ability to assess dataset quality and anticipate its impact on model training.

Nice to haves

• Experience with distributed training frameworks (e.g., JAX, PyTorch, FSDP, Megatron).

What you'll be doing

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

Perks and benefits

• Weekly lunch stipend of $75/£75 or equivalent in local currency.
• Full health and dental benefits, including a separate mental health budget.
• Retirement plans including RRSP matching, 401K, or Pension Scheme.
• 100% parental leave top-up for up to 6 months for either parent.
• Annual enrichment benefits covering arts & culture, fitness/wellness, quality time, workspace improvements, and education & learning stipends.
• Six weeks of paid vacation (30 working days).
• Budget for travel to other offices if remote, plus an annual company offsite.
• Remote-friendly work environment with offices worldwide and benefits like daily lunch, snacks, community events, co-working benefits, and a $500 home office stipend.