Sneha S.

My background is in Machine Learning Engineering, with a strong focus on building scalable AI and LLM-driven systems for real-world production environments, especially in fashion e-commerce. Over the past 5+ years, I’ve worked extensively on transforming unstructured data into actionable business value through end-to-end AI solutions.

I specialize in Large Language Models (LLMs) and vision-language pipelines, and I’ve built systems that go beyond experimentation - they scale reliably in production. My experience includes automating product tagging, attribute extraction, and catalog enrichment using models like GPT, LLaMA 2/3, Claude Sonnet, and various Hugging Face models. I’ve also deployed containerized LLM applications using LangChain and integrated them into enterprise workflows.

On the engineering side, I design microservice-based architectures using FastAPI and Django, and I’m fluent in Python and modern deployment practices. I’ve also built RAG-based chatbots and retrieval systems that enable enterprises to interact with their internal data more intelligently.

Overall, my focus is on bridging AI research with practical, production-grade solutions that improve retail operations, enhance product discovery, and deliver measurable business impact.