Hi, I'm
I build
Lead Engineer with 5 years of hands-on experience developing and deploying GenAI, RAG, Agentic AI, and deep learning systems from scratch. I build production-grade AI platforms for realtime voice interaction, enterprise knowledge retrieval, regulatory search, and automated finance analysis. My work spans NLP, autonomous driving, computer vision, and Camera-LiDAR-Radar fusion, with a focus on reliable architecture, model optimization, and scalable data pipelines.
Stack: Python, GCP, GenAI, LLMs, Agents, Docker, FastAPI, Cloud SQL, Google ADK, Vertex AI, Agent Engine, Cloud Run, OpenAI Realtime API, WebSockets, Redis, MongoDB, Milvus, JWT, Docling, BM25, ModernBERT, vLLM, and FAISS.
Production systems I led and shipped
Gemini/Google ADK agents on Vertex AI for invoice anomaly detection and FP&A variance analysis
Production realtime voice AI with OpenAI Realtime API, Milvus RAG, and live human handoff
Production hybrid RAG and citation-grounded answers over SEBI legal and regulatory documents
Qualcomm realtime edge pipeline with 75% CPU runtime reduction
SOLOv2 BEV segmentation, OpenCV image blending, and multi-model classification
PyTorch/TensorFlow accelerator suite with TPC kernels, ONNX export, and Netron validation
Firebase telemetry pipelines, on-demand preprocessing, and Baum-Welch HMM estimation
What I use to ship production AI
HCL Technologies Limited, Noida
Tech lead for production GenAI platforms across finance automation, realtime voice AI, and regulatory search. Designed systems for production reliability, latency, secure deployment, and operational handoff.
Stack: Python, FastAPI, Google ADK, Vertex AI, OpenAI, Milvus, Redis, MongoDB, Docker, GCP.
HCL Projects
IFRS — Invoice anomaly detection and FP&A variance analysis with Gemini/Google ADK, SAP data validation, and Vertex AI deployment.
AACA — Production realtime voice AI with Twilio, OpenAI Realtime API, Milvus RAG, structured tool calling, and live human handoff.
SEBiSearch — Offline regulatory RAG with hybrid Jina/BM25 retrieval, ModernBERT reranking, citation-constrained generation, and Redis/FAISS caching.
PathPartner Technology (KPIT), Bangalore
Shipped edge vision and accelerator software across computer vision, BEV segmentation, and deep learning kernel optimization. Built production C++ pipelines, trained vision models, and mapped deep learning operators to accelerator kernels.
PathPartner / KPIT Projects
Image Stitching — ONNX and C++ feature detection/matching pipeline on Qualcomm, reducing CPU runtime by 75%.
CES — SOLOv2 training, OpenCV BEV blending, multi-model segmentation/classification, and LIME visualization.
Deep Learning Kernels — PyTorch/TensorFlow to TPC kernels in C++, with ONNX and Netron delivery.
AgVerse Technology, Bangalore
Built Firebase telemetry and ML data-processing foundations during an engineering internship, including on-demand preprocessing and Baum-Welch HMM parameter and state estimation.
AgVerse Project
AgVerse Analytics — Firebase telemetry, on-demand preprocessing, and Baum-Welch HMM estimation.
Indian Institute of Technology (IIT) Bhilai
Discover Artificial Intelligence 2026 + IEEE ICRAIS 2023 — one Best Paper
Discover Artificial Intelligence 2026.
IEEE ICRAIS 2023.
IEEE ICRAIS 2023.
Let’s build something reliable together
Open to Staff/Lead roles in Applied AI and collaborations on voice agents and domain RAG. Fastest response by email.