Research Engineer, Production Model Post Training

📋 Description

• Train base models via post-training stack for production Claude models.
• Implement, scale post-training techniques like Constitutional AI and RLHF.
• Design, build, and run robust pipelines for model fine-tuning and evaluation.
• Develop tools to measure and improve model performance across dims.
• Collaborate with research teams to translate techniques into prod-ready implementations.
• Debug complex issues in training pipelines and model behavior.
• Help establish best practices for reliable, reproducible post-training.

🎯 Requirements

• Strong Python and deep learning framework skills.
• Experience training, fine-tuning, or evaluating large language models.
• Experience with large-scale distributed systems and HPC.
• Ability to balance research exploration with engineering rigor and reliability.
• Strong debugging skills for training pipelines and model behavior.
• Collaborative across research and engineering teams.
• Comfortable with fast-paced, ambiguous environments.

🎁 Benefits

• Competitive compensation and benefits.
• Optional equity donation matching.
• Generous vacation and parental leave.
• Flexible working hours.
• Office space for collaboration.