AI Research Assistant, Tech Innovation Lab
Served as an AI Research Assistant evaluating large language model (LLM) outputs across multiple domain-specific tasks. Built and tested targeted prompts to assess model performance, reasoning capabilities, and knowledge boundaries. Produced detailed feedback and improvement recommendations based on systematic evaluation criteria.• Evaluated LLM responses for coding, writing, and analytical tasks.• Designed prompt sets to probe reasoning and knowledge limits.• Documented constructive feedback and recommendations using evaluation criteria.• Completed asynchronous evaluation projects with independent execution and flexible scheduling.