Systems Engineer II — National Centre for Artificial Intelligence and Robotics (NCAIR) | AI/LLM/RAG evaluation and system performance assessment
DocumentServed as Systems Engineer II conducting systematic evaluation of AI and robotics research outputs, with emphasis on assessing technical correctness, accuracy, relevance, and reasoning quality. Translated feasibility-analysis skills into criteria-based review of AI-generated Python/code and generative AI (RAG/LLM) responses. Worked on engineering solutions that support automated question answering over business documents to enable content-level evaluation. • Evaluated LLM/RAG outputs for accuracy and relevance during system-building • Assessed Python code for correctness, efficiency, and style • Performed technical feasibility analysis and system performance evaluation • Designed/implemented RAG workflows supporting document-grounded Q&A for testable outputs