Research Engineer, Production Model Post-Training

Anthropic is a public benefit corporation focused on creating reliable AI systems. The Research Engineer in the Post-Training team will enhance production models through sophisticated post-training processes and collaborate with research teams to implement cutting-edge techniques that improve model quality and safety.

Responsibilities:

• 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