Research Engineer, Reward Models

Job Description

Anthropic is seeking a Research Engineer to join their Reward Modeling team. The company's mission is to create reliable, interpretable, and steerable AI systems that are safe and beneficial. The Reward Modeling team focuses on developing techniques for teaching AI systems to understand and embody human values, as well as advancing AI capabilities.

The Research Engineer will contribute to the science of reward modeling.

Responsibilities:

• Help implement novel reward modeling architectures and techniques
• Optimize training pipelines
• Build and optimize data pipelines
• Collaborate across teams to integrate reward modeling advances into production systems
• Communicate engineering progress through internal documentation and potential publications

Requirements:

• Strong engineering background in machine learning, with expertise in preference learning, reinforcement learning, deep learning, or related areas
• Proficiency in Python, deep learning frameworks, and distributed computing
• Familiarity with modern LLM architectures and alignment techniques
• Experience with improving model training pipelines and building data pipelines
• Comfort with the experimental nature of frontier AI research
• Ability to clearly communicate complex technical concepts and research findings
• Deep interest in AI alignment and safety
• Bachelor's degree in a related field or equivalent experience

What Anthropic Offers:

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