AI/GenAI Prompt Engineer (LLM Prompt Output/RAG Pipeline)
Developed and maintained structured prompt templates and outputs for large language model (LLM) powered systems. Designed, implemented, and evaluated Retrieval-Augmented Generation (RAG) pipelines combining enterprise data sources and contextual prompt formats for AI model output consistency. Worked directly with LLM APIs (OpenAI, Azure OpenAI) to tune response generation and facilitate automated document understanding with model output benchmarking. • Implemented LLM prompt engineering and deterministic output templates • Conducted structured output evaluation and response benchmarking • Tuned AI responses for document understanding and contextual generation • Used internal/proprietary tools and Azure cloud infrastructure for AI development