Applied AI Researcher | Applied AI Engineer | Ph.D., IIT Delhi
I specialize in Agentic Frameworks, LLM Optimization, and turning wild AI ideas into scalable production reality. If it hallucinates, I tame it. If it's too big, I compress it! 🗜️🧠
🌐 Website • 📫 Email • 💼 LinkedIn • 🎓 Google Scholar • 📄 Resume/CV
- AI Consultant / Applied AI Engineer @ KPMG: Architecting and deploying Enterprise-Scale Agentic Solutions. I recently engineered to production a globally adopted skill-based agentic platform using FastAPI, React, and Azure OpenAI.
- Vibe-Coding Full-Stack: Bridging the gap between cutting-edge AI research and slick, scalable, containerised applications.
- Trusted AI Governance: Applied entropy-based metrics and Bayesian estimation for pre- and post-generation hallucination detection
- Explored next-generation agent generation paradigms through two PoCs: an "Agentic Factory" for dynamic synthesis and deployment of task-specific autonomous agents from natural language instructions, and a skill-based agentic orchestration framework for automated, multi-step enterprise workflows.
To get a taste of how I architect AI systems, check out my open-source work:
- 🏗️ EvalAgent – An open-source architecture demo of a full-stack agentic evaluation platform. Built with a FastAPI backend, async SQLAlchemy, redis, celery , Azure OpenAI integration, and a React frontend.
- 🧠 Efficient AI & LLM Compression – During my Ph.D., I developed VTrans (10× speed-up for LLM fine-tuning) and its upgraded version, TVA-prune (60% GPU inference speed-up for LLaMA/Mistral).
- 🏃 Action Recognition Compression – Designed algorithm achieving over 70x compression and ~100x Raspberry Pi speedup vs. full LSTMs. Code Repo
- AI/ML Jedi Skills: Multi-Agent Systems, Structured Tool Calling, LLM Compression & Quantization (LoRA, PEFT), Hardware-Aware NAS.
- Languages & Frameworks: Python, PyTorch, LangChain, FastAPI, React.
- MLOps & Deployment: Docker, Azure (App Service, OpenAI, Blob Storage), CI/CD pipelines, async architectures.
- Research Chops: Published at top-tier venues including ICML and WACV.
- I can accelerate LLM fine-tuning by 10x, but I still can't speed up my morning coffee brewing process. ☕
- From coding precise lunar landings (IISc Internship) to deploying enterprise multi-agent systems, I love making complex architectures land smoothly! 🌕🚀
Looking for an Senior AI Engineer or an AI Solution Architect or an Applied Researcher who can speak both "deep learning math" and "production architecture"? Let's talk!