Prompt Engineer and AI Workflow Specialist
Oversaw the design and implementation of AI workflows focusing on prompt engineering for Large Language Models. Responsible for developing, refining, and evaluating prompts to maximize accuracy and output relevance in retrieval-augmented generation (RAG) architectures. Authored and tested prompts to enable secure and real-time LLM access to business data for downstream AI applications. • Developed complex prompts for generative AI tasks, including text summarization and question answering. • Conducted iterative prompt revisions to improve AI agent accuracy in business processes. • Evaluated prompt-based outputs for logic, correctness, and relevance to application domain. • Utilized Pinecone and Weaviate in conjunction with prompt engineering frameworks.