LLM Application Developer and Prompt Engineer
Worked extensively on building LLM applications and Retrieval-Augmented Generation (RAG) pipelines involving prompt engineering and optimization. Developed structured reasoning pipelines, semantic search tasks, and prompt optimization strategies for text-based AI systems, focusing on Q&A and knowledge retrieval tasks. Utilized skills in prompt crafting, data curation for fine-tuning, and iterative evaluation of LLM-generated outputs. • Developed, tested, and refined LLM prompts to optimize AI output for specialized domains • Worked on chunking strategies to improve semantic retrieval of document text • Designed and performed evaluations of AI-generated answers for accuracy and relevance • Participated in research involving prompt-based fine-tuning for text applications