New Delhi, Delhi, India
AI Engineer building production-grade LLM systems at enterprise scale. Architected multi-tenant, GPT-4 powered RAG platforms integrating vector search, knowledge graphs, and governed agent orchestration to deliver secure, compliant AI automation. Experienced in scaling AI infrastructure across 50+ enterprise tenants, processing 1M+ records through Azure- based Bronze-to-gold data pipelines, and optimizing latency, retrieval precision, and token efficiency through structured evaluation frameworks. Strong foundation in FastAPI, Docker, and Azure cloud deployment, with a focus on reliability, Audibility, and real-world AI impact.