Prashant J.

About Prashant J.

Lead Data Scientist at Deloitte, driving innovation with GenAI and LLMs. I specialize in fine-tuning, quantization, and deployment of large language models like LLaMA 3.1 and GPT-4.0 using vLLM and Retrieval-Augmented Generation (RAG) techniques.I’ve built production-ready AI systems — from a voice-based interview platform with real-time STT/TTS (Deepgram, Twilio) to resume parsers and JD matching engines using embeddings + vector DBs (Qdrant). My work bridges cutting-edge research and practical deployment, turning complex business problems into scalable AI solutions.Key areas: LLM fine-tuning & 4-bit deployment GenAI pipelines & prompt engineering Real-time inference (TTFT:~6ms) Voice AI, RAG, Vector Search AWS, vLLM, HuggingFace, Python stackAlways open to discussing GenAI use cases, applied NLP, and real-time AI deployments.

Experience

1. Deloitte

   Present