About the Role

Research Engineer Intern at AgentHub, working directly with founders to advance AI agent evaluation and simulation capabilities. You'll research and implement state-of-the-art methodologies for evaluating agents across safety, reliability, and efficiency. This role involves translating research into real features for customers at the frontier of AI.

Key Responsibilities

• Design and build core methodologies for evaluating agents across instruction following, safety, groundedness, and efficiency
• Research, experiment, and implement robust data generation capabilities
• Tie in latest research advancements and productionalize them for customer value
• Build scalable systems for ingesting, storing, and analyzing structured/unstructured agent outputs
• Design evaluation pipelines capturing reasoning, safety, reliability, and edge-case behavior

Required Skills & Qualifications

Must Have:

• Working towards Bachelors/Masters/PhD in Computer Science or related field
• Passionate about building category-defining products
• Previous background and experience in reinforcement learning
• Opinionated, perpetually curious, and love having scope over problems and delivering

Nice to Have:

• Demonstrated experience in model/agent evaluation