Member of Technical Staff - Post-Training (Reinforcement Learning & Generalization)

Highlights

• Train large language models to truly learn skills beyond training tasks.
• Build held-out evaluations measuring generalization to unseen domains.
• Turn successful research into robust recipes for production models.

What they offer

• Equity
• Weekly lunch stipend
• Full health and dental benefits including mental health budget
• RRSP matching, 401K, Pension Scheme
• 100% parental leave top-up for up to 6 months
• Annual enrichment benefits and education stipend
• 6 weeks of paid vacation
• $500 home office stipend and co-working benefit
• Travel budget and annual company offsite

Ideal candidate

A rigorous experimentalist passionate about LLM post-training and generalization, who loves diving into data and training dynamics to turn research insights into reliable production recipes.

Requirements

• Strong research and software engineering skills with hands-on experience training LLMs
• Experience applying reinforcement learning to LLMs, ideally at scale
• Track record on generalization, robustness, or distribution shift via publications or shipped models
• Rigorous experimental practice with clean ablations and careful controls
• Experience with distributed training is a plus
• Excellent communication skills
• Deep understanding of data quality principles and impact on training