Research Engineer, Production Model Post-Training

Anthropic's production models undergo sophisticated post-training processes. As a Research Engineer on the Post-Training team, you'll train base models through the complete post-training stack to deliver production Claude models. You'll work at the intersection of research and production engineering, implementing, scaling, and improving post-training techniques like Constitutional AI, RLHF, and other alignment methodologies.

• Implement and optimize post-training techniques at scale on frontier models
• Conduct research to develop and optimize post-training recipes that directly improve production model quality
• Design, build, and run robust, efficient pipelines for model fine-tuning and evaluation
• Develop tools to measure and improve model performance across various dimensions
• 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

You may be a good fit if you thrive in controlled chaos, adapt quickly, maintain clarity when debugging complex issues, have strong software engineering skills with experience building complex ML systems, are comfortable with large-scale distributed systems and high-performance computing, have experience with training, fine-tuning, or evaluating large language models, can balance research exploration with engineering rigor, are adept at analyzing and debugging model training processes, enjoy collaborating across disciplines, and can navigate ambiguity. Strong candidates may also have experience with LLMs and a keen interest in AI safety. Proficiency in Python, deep learning frameworks, and distributed computing is required.

Annual Salary: $350,000—$500,000 USD

Minimum education: Bachelor’s degree or equivalent. Hybrid policy: at least 25% in office. Visa sponsorship available. All interviews in Python. May require responding to incidents on short-notice, including weekends.