Zeeshan Zafar

I'm an AI Engineer with over 1.5 years of hands-on experience designing, building, and deploying AI-driven solutions, primarily focused on Generative AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG) pipelines. I’ve worked with two companies where I’ve led end-to-end development of production-ready AI applications—from model fine-tuning to backend integration and deployment.

My core strength lies in building LLM-powered applications using tools like LangChain, LlamaIndex, Hugging Face Transformers, Qdrant, FAISS, and FastAPI. I’ve fine-tuned models using LoRA/QLoRA techniques, managed vector databases, and built scalable AI systems deployed on Azure, AWS, and Hugging Face Spaces.

Some of my key projects include:

• Antobot – an anatomy learning chatbot with real-time 3D visualization and quiz generation.
• AI Lead Generation Bot – a fully automated LinkedIn lead scraping and outreach tool with a RAG-based assistant.
• AI Storytelling Bot – a generative storytelling tool with mood-based illustrations powered by diffusion models.

I also have experience developing robust backends using FastAPI and creating interactive UIs with Next.js, Gradio, Streamlit, and Chainlit to enhance end-user experience. My deployments are containerized using Docker and hosted on cloud platforms for scalability and performance.

What sets me apart is my ability to not just build AI models, but to deliver end-to-end AI solutions—from data preprocessing and model training to API development, frontend integration, and cloud deployment. I love working on challenging problems where AI can create real impact.

Whether you're looking to build an intelligent chatbot, integrate a custom LLM into your product, or develop a full-stack AI solution, I can help bring your idea to life quickly and effectively.

Let’s connect and build something intelligent together!