Zoya Qureshi

I am an AI Engineer experienced in building and deploying LLM-powered applications, optimizing ML pipelines, and implementing MLOps workflows. I have delivered scalable solutions across domains — medical chatbots, NFT generators, wearable AI — leveraging LangChain, FAISS, HuggingFace, Docker, AWS, and FastAPI to improve accuracy and reduce latency.

I consistently focus on modular, reusable systems and automation: I have improved preprocessing pipelines, implemented caching strategies, deployed FAISS-backed agents, and created reusable NLP components to accelerate deployments. I seek roles where I can drive production-grade GenAI solutions and scale ML systems end-to-end.