Generative AI Engineer (Freelance)
As a Generative AI Engineer, I designed and deployed production-ready LLM applications with a focus on AI training tasks. I specialized in fine-tuning foundation models and retrieval-augmented generation (RAG) pipelines, applying advanced prompt engineering techniques throughout. My work included building semantic retrieval pipelines and QA systems requiring robust data preparation and model adaptation. • Fine-tuned LLMs such as Llama2 for specific domains and evaluated improvements over baseline models. • Developed, annotated, and curated textual datasets for LLM training and supervised AI evaluation. • Built pipelines for semantic search and context-aware response generation, requiring precise data and prompt curation. • Integrated tools like OpenAI, Pinecone, LangChain, and Flask for training, annotation, and deployment tasks.