Become an AI Evaluation Intern at Themis Intelligence, where you will engage with LLM agent behaviors throughout a 12-month co-op experience. This role offers a chance to analyze and evaluate AI outputs.

Themis Intelligence invites students interested in machine learning and AI systems to apply for this co-op position. You will participate in evaluating Themis Agents and ensuring model accuracy while handling systematic experiments and analyses. This opportunity is designed for individuals who enjoy debugging and exploring AI functionalities in depth.

Key Responsibilities: • Evaluate output accuracy and consistency of AI agents • Analyze grounding issues when models deviate from knowledge • Score and compare AI performance across different tasks • Build Python evaluation pipelines with various frameworks • Visualize experiment results and organize data analysis

Requirements: • Currently pursuing a Bachelor’s degree in relevant fields • Completed courses in ma...