Research Engineer, Production Model Post-Training

The role

You will train base models through the complete post-training stack to deliver production Claude models. You will implement, scale, and improve post-training techniques like Constitutional AI and RLHF.

What you will do

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

Required qualifications

• Strong software engineering skills with experience building complex ML systems
• Comfortable working with large-scale distributed systems and high-performance computing
• Experience with training, fine-tuning, or evaluating large language models
• Adept at analyzing and debugging model training processes
• Proficiency in Python
• Proficiency in deep learning frameworks
• Proficiency in distributed computing
• Bachelor’s degree or an equivalent combination of education, training, and/or experience
• A field relevant to the role as demonstrated through coursework, training, or professional experience

Nice to have

• Experience with LLMs
• A keen interest in AI safety and responsible deployment
• Senior engineers with hands-on experience with frontier AI systems

Benefits

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Lovely office space

Before you apply

• All interviews are conducted in Python
• Role may require responding to incidents on short-notice, including on weekends
• We do sponsor visas

About the company

Anthropic is a public benefit corporation headquartered in San Francisco. Its mission is to create reliable, interpretable, and steerable AI systems.