soumyad

AI Engineer and Researcher with hands-on expertise in developing and deploying large language models (LLMs) like GPT, BERT, and T5 for complex NLP workflows. I specialize in Retrieval-Augmented Generation (RAG) systems, autonomous LangChain agents, and full-stack AI engineering — from fine-tuning to scalable deployment using FastAPI, Docker, and AWS (EC2, Lambda, SageMaker).

At Lancers Technology, I’ve led the development of Q&A systems, smart contract automation bots, and AI ops pipelines with end-to-end ownership. My work blends deep learning research with cloud-native deployment, ensuring every model I build is optimized, robust, and ready for real-world production environments.