About
I'm an AI Engineer focused on building and deploying production-grade Generative AI and LLM-powered systems. My experience spans LLM infrastructure, model serving, RAG (Retrieval-Augmented Generation), AI agents, Document AI, and scalable backend systems. In my current role, I build enterprise AI platforms that support document understanding, semantic search, financial intelligence, and multimodal AI workloads. I've worked on LLM serving using vLLM and LiteLLM, LLM inference optimization, GPU utilization, request scheduling, AI evaluation, and production deployment of Large Language Models. I have hands-on experience with RAG pipelines, vector databases (Milvus, FAISS), embedding models, LangChain, LangGraph, MCP, and enterprise AI workflows. My technical stack includes Python, FastAPI, Django, PyTorch, SQL, Docker, Kubernetes, OpenShift, REST APIs, microservices, and distributed systems. I've built scalable AI services for document processing, retrieval, semantic search, KPI normalization, and AI-assisted business workflows.
Work experience
Data Scientist 2 at Deloitte, Sep 2025 - Present · 1 yr, Bengaluru, Karnataka, India
Software Engineer at Mowito, Aug 2024 - Sep 2025 · 1 yr 2 mos, Bengaluru, Karnataka, India
Co-Founder at Fond Solutions Pvt. Ltd., May 2022 - Apr 2024 · 2 yrs, Karnataka, India
