Research Engineer, Post-Training

📋 Description

• Drive post-training experiments to improve agent performance within cost, latency, and governance.
• Optimize agent harnesses, including domain-specific skills and retrieval strategies.
• Design and develop grading and reward systems for high-stakes legal work.
• Study agent behavior and convert findings into training data or harness changes.
• Collaborate with researchers and external partners to drive concrete model improvements.

🎯 Requirements

• Hands-on post-training or model-training experience (SFT, RLHF, RLAIF).
• Strong judgment of model behavior; read traces and identify failure modes.
• Strong Python and research-engineering ability; write code and debug experiments.
• Ability to self-manage ambiguous applied research and communicate clearly with teams.

🎁 Benefits

• Hybrid work model with collaboration across teams.
• Opportunity to work on a rapidly growing company with global impact.
• Global customer base across 70+ countries.
• Equal opportunity employer; accommodations available.