
0
0
7+ years of experience
I’m an AI-focused full-stack engineer specializing in Retrieval-Augmented Generation (RAG), LLM orchestration, and advanced prompt engineering. I design and build intelligent systems that combine structured data, vector search, and large language models to deliver reliable, scalable, and context-aware AI solutions. With hands-on experience in designing RAG pipelines (ingestion, chunking, embedding, retrieval, and reasoning), I work with technologies such as LangChain, Redis Vector Search, FAISS, Azure OpenAI, and FastAPI to build real-world AI applications, including chatbots, document analysis systems, and automated decision pipelines. I focus on optimizing prompts and workflows to improve model accuracy, reduce hallucinations, and align AI outputs with business logic and domain constraints. My approach combines engineering rigor with experimentation, enabling rapid prototyping and high-performance AI systems in complex domains like insurance, education, and legal compliance. Passionate about hackathons and innovation, I enjoy transforming ideas into intelligent products by leveraging RAG architectures, agent-based systems, and modern LLM capabilities.