Research Engineer, Production Model Post Training

Job Description

Anthropic is seeking a Research Engineer to join their Post-Training team. In this role, the individual will be responsible for developing and optimizing systems that enhance the capabilities, alignment, and safety of Anthropic's production models. The Research Engineer will work at the intersection of research and production engineering, implementing and scaling post-training techniques such as Constitutional AI and RLHF.Role involves:

• Implementing and optimizing post-training techniques at scale.
• Designing, building, and running robust pipelines for model fine-tuning and evaluation.
• Developing tools to measure and improve model performance.
• Collaborating with research teams to translate emerging techniques into production-ready implementations.
• Debugging complex issues in training pipelines and model behavior.
• Establishing best practices for reliable, reproducible model post-training.

Requirements:

• Strong software engineering skills with experience building complex ML systems.
• Comfort working with large-scale distributed systems and high-performance computing.
• Experience with training, fine-tuning, or evaluating large language models.
• Ability to balance research exploration with engineering rigor and operational reliability.
• Proficiency in Python, deep learning frameworks, and distributed computing.
• Bachelor's degree in a related field or equivalent experience.

Anthropic offers:

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