Research Engineer, Production Model Post-Training

Overview

Research Engineer on Anthropic’s Post-Training team, training base models through a complete post-training stack to deliver production Claude models.

What you'll do

• Implement and optimize post-training techniques at scale on frontier models.
• Research and optimize post-training recipes that improve production model quality.
• Design, build, and run pipelines for model fine-tuning and evaluation.
• Develop tools to measure and improve model performance across dimensions.
• Collaborate with research teams to translate emerging techniques into production implementations.
• Debug complex issues in training pipelines and model behavior.
• Help establish best practices for reliable, reproducible post-training.

What you'll need

• Experience building complex ML systems with strong software engineering skills.
• Comfort working with large-scale distributed systems and high-performance computing.
• Experience with training, fine-tuning, or evaluating large language models.
• Proficiency in Python, deep learning frameworks, and distributed computing.
• A bachelor’s degree or an equivalent combination of education, training, and/or experience.

Details

• Interviews are conducted in Python.
• May require responding to incidents on short notice, including weekends.
• Hybrid policy: in one of the offices at least 25% of the time.
• Visa sponsorship is available, though not for every role/candidate.