Headline

AI Engineer | Generative AI & LLM Systems | RAG · MCP · A2A · Agentic Workflows | Deploying Transformer Models at Scale on GCP & Azure | 7+ Years in Production AI

About

I don't just build AI models — I build AI that works in production. AI Engineer with 7+ years specializing in Generative AI, LLM pipelines, RAG architectures, and agentic workflows (MCP, A2A). At DecisionPro, I've shipped document intelligence platforms, LLM-powered classifiers, and real-time ML systems on GCP and Azure — end to end, at scale.

Location

Delhi

Work experience

Data Scientist at DecisionPro, Inc, Jul 2016 - Present · 10 yrs, Remote, 🤖 Generative AI & Agentic Document Intelligence Architected an end-to-end Generative AI pipeline using transformer-based LLMs, enabling intelligent document categorization and context-aware semantic search across enterprise repositories Engineered agentic AI workflows with multi-step reasoning chains, implementing MCP (Model Context Protocol) and A2A (Agent-to-Agent) interaction patterns for autonomous document processing Deployed a hybrid RAG architecture combining FAISS vector similarity search with structured queries, improving LLM grounding and contextual retrieval accuracy by reducing irrelevant results Containerized and deployed scalable model inference pipelines using Docker on Azure Kubernetes Service (AKS), ensuring production-grade availability and horizontal scalability 🧠 LLM Fine-tuning & NLP Classification Fine-tuned BERT and GPT-family models for multi-class ticket classification, automating customer support routing across thousands of daily conversations Built automated CI/CD workflows for model training and deployment using Kubeflow Pipelines, cutting manual deployment effort and enabling continuous model improvement Optimized model inference for production SLAs and integrated via REST APIs into live customer-facing microservices, reducing response latency 📊 Predictive AI & Cloud Deployment (GCP) Designed and deployed customer purchase prediction models on Google Cloud AI Platform, enabling real-time inference for high-throughput transactional workloads Engineered features from large-scale MySQL datasets using Python (Pandas, NumPy), applying statistical modeling and EDA to surface key behavioral signals driving purchase decisions

Market and Competitive Analyst at Technicolor, Feb 2016 - Jul 2016 · 6 mos, Greater Rennes Metropolitan Area, Deliver key insights of the analytics markets for IoT and Set-Top Box: 1. Study of different growth axes of the company and proposing action plans to achieve objectives 2. Study of the sales strategy of the main competitors 3. Perform functional benchmarks of competitive solution and analyze gaps versus Technicolor solutions 4. Building the business case to be presented to the steering committees.

Intern at Siemens, May 2013 - Jul 2013 · 3 mos, Greater Bengaluru Area, Monitoring of Vehicles and Activities inside Open Pit Lignite Mines 1. Real time analysis of movement of vehicles and mining operations through mobile and desktop applications. 2. Creation of Database for various kinds of activities and vehicles inside mines and their representation on Google Maps. 3. Increased efficiency of monitoring from single source and improved safety measures inside mines.

Industrial Trainee at HCL Infosystems Ltd, Dec 2011 - Jan 2012 · 2 mos, Noida, Uttar Pradesh, India, Creation of application for Hospital Management for HCL ME Tablets 1. Requirement Analysis, development and testing of application within a team of 5. 2. Creation of database and interface for server for Hospital Management. 3. Increased efficiency of Hospital staff and Doctors in tracking their patients’ health.

Education

Masters in Management, Business Analytics and Marketing, ESSEC Business School

MBA Exchange, Business Analytics and Marketing, University of California, Irvine - The Paul Merage School of Business