Evaluation Engineer Intern

About this role

About the role: - Test and validate generative AI systems and language models by designing comprehensive evaluation scenarios - Write Python or JavaScript code to call APIs, process model outputs, and verify correctness of results - Create automated checks that identify inconsistencies, edge cases, and failure modes in AI-generated responses - Document findings clearly with structured reports and communicate results to the team - Spot patterns in test results that reveal how systems behave under different conditions What you'll work on: - Building evaluation frameworks that assess the performance and reliability of AI tools and LLMs - Designing test cases covering functional behavior, regression risks, and boundary conditions - Using AI systems themselves to generate evaluation data and design test scenarios - Debugging test failures and refining checks based on what you learn - Working with REST APIs, JSON data structures, and SQL queries to validate outputs - Collaborating with a product team that moves at speed and values rapid iteration What we're looking for: - Bachelor's degree in Computer Science, IT, or a closely related field - Hands-on experience with generative AI tools and LLMs, demonstrated through GitHub projects or similar work - Solid grasp of software development practices and core testing principles - Proficiency in Python or JavaScript for scripting and automation - Sharp analytical and logical thinking, with the ability to reason through complex problems - Keen eye for detail and a methodical approach to documentation - Clear communication skills, both written and spoken Good to know: - Git experience for version control and collaboration will serve you well - Familiarity with REST APIs, JSON formats, and basic database concepts is valuable - Experience designing test cases for functional, regression, and edge-case coverage is a plus - Comfort learning new tools and adapting to a dynamic, fast-moving environment