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.