Post-Training Applied Researcher

📋 Description

• Design and run post-training pipelines (SFT, GRPO, DPO, RLVR)
• Build task-specific training environments and evals for healthcare, code, and legal
• Translate production data into training signals; design reward loops
• Run end-to-end training experiments; diagnose reward hacking and drift
• Publish findings and contribute to Baseten's open-source training libraries

🎯 Requirements

• Hands-on LLM training with reinforcement learning (GRPO/PPO)
• Strong reward engineering intuition; distinguish effective vs exploitable rewards
• Experience building multi-turn agent environments with tool use
• Comfort with end-to-end ML pipeline from data to deployment
• Experience with production ML systems; prefer closed-loop production data
• Experience with RL training frameworks
• Publications at NeurIPS/ICML/ICLR on RL for LLMs, reward modeling, or alignment

🎁 Benefits

• Competitive pay with meaningful equity
• 100% medical, dental, and vision for you and dependents
• Generous PTO including Winter Break
• Paid parental leave
• Company-facilitated 401(k)
• Exposure to ML startups for learning/networking