Post-Training Applied Researcher

Highlights

• Post-train open models to outperform frontier closed models on specialized tasks.
• Models you train ship to production and reach millions of users.
• Work directly with stakeholders from the world’s fastest-growing AI companies.

What they offer

• Meaningful equity (U.S. only)
• 100% coverage of medical, dental, and vision insurance for employee and dependents
• Flexible PTO including company-wide Winter Break
• Paid parental leave
• Fertility and family-building stipend through Carrot (U.S. only)
• Company-facilitated 401(k)

Ideal candidate

Hands-on RL researcher excited to ship models to production, translating customer domain needs into training curricula and balancing rigor with fast iteration.

Requirements

• Hands-on experience training LLMs with reinforcement learning including GRPO or PPO, group advantage computation, clipped objectives, and KL penalty design
• Strong intuition for reward engineering and distinguishing rewards that train effectively vs exploit at scale
• Experience building multi-turn agent environments with tool use
• Comfort working across full pipeline from dataset construction through training, evaluation, and deployment
• Experience with production ML systems, preferably closing training-inference loop with production data