Hire the Best Computer Vision Engineers
in India

I build production multimodal AI systems that turn images, documents, and business data into reliable outputs. My recent work includes reference-based visual reasoning and image-generation pipelines with deterministic answer and uniqueness validation, SVG/PNG rendering, bilingual content, and secure FastAPI/Docker APIs. I also build production AI agents and RAG systems that connect LLMs to private documents, databases, APIs, and enterprise workflows. I own the lifecycle from requirements and architecture through structured model outputs, programmatic validation, deployment, and handover. SELECTED RESULTS • Built and deployed Visual Reasoning AI Studio, a reference-based multimodal AI question-generation and deterministic verification platform with a live synthetic showcase in my Upwork portfolio. • Delivered non-verbal image reconstruction and .NET/API integration for an education workflow. • Built a real-time multi-agent cybersecurity platform that improved incident-response speed by 40%. • Delivered an image-to-data pipeline with 95%+ accuracy across complex document types. • Built natural-language-to-SQL assistants for non-technical teams. WHAT I BUILD • Multimodal AI, computer vision, image processing, and document intelligence • Reference-based image and diagram generation with structured visual outputs • AI agents and multi-agent workflows using LangGraph, LangChain, AutoGen, and LlamaIndex • Production RAG, extraction, classification, and structured-output pipelines • FastAPI, Docker, MCP, API, ERP, and business-workflow integrations • Azure/AWS deployment, evaluation, security, and human-approval controls CORE STACK Python, FastAPI, OpenAI, Azure OpenAI, AWS Bedrock, LangGraph, LangChain, LlamaIndex, AutoGen, MCP, computer vision, OCR, SVG/PNG rendering, PostgreSQL, Docker, Kubernetes, Databricks, and Kafka. WHY CLIENTS HIRE ME • Production systems, not isolated prompt demos • Full-stack AI ownership from architecture through deployment • Deterministic validation for correctness, uniqueness, and output consistency • Clear communication, documented decisions, and realistic estimates If you are building a multimodal AI, computer-vision, visual-reasoning, RAG, or enterprise LLM application, send me the current system and desired outcome. I will propose the smallest reliable path to production.

I build production-grade Generative AI systems — RAG pipelines, LLM-powered agents, and document-intelligence tools that turn unstructured data into measurable business results. Over the past 4+ years, I've designed and shipped GenAI solutions for a Fortune 500 semiconductor client, including: A RAG-based compliance system (Azure OpenAI + FAISS, 5,000+ indexed rules) that cut manual document review time by 70% and hit 92% accuracy in flagging policy violations. A Graph RAG + Vector RAG hybrid multi-agent workflow (Neo4j + LangGraph) enabling multi-hop reasoning across technical documents — well beyond what flat semantic search can do. LLM-driven ticket summarization & classification pipelines that reduced manual triage effort by 80%. Vision-Language Model (VLM) extraction pipelines combining OCR, Azure Document Intelligence, and GPT-4o to pull structured data out of engineering drawings and patents. I work across the full GenAI stack — from prompt engineering and function calling/tool use to vector databases, hybrid search & reranking, and scaled deployment on Azure/Databricks with FastAPI + PostgreSQL backends. I hold an MTech in Data Science from IIT Palakkad and have a Computer Vision engineering background (YOLOv6/7/8, OCR, video analytics), so I'm equally comfortable when a project blends GenAI with vision or classic ML. What I can help you build: RAG pipelines & knowledge assistants (FAISS, Pinecone, Neo4j/GraphRAG) LLM agents & multi-step agentic workflows (LangChain, LangGraph, function calling) Document AI: extraction, classification, and compliance automation from PDFs/DOCX/scanned docs LLM-powered automation: summarization, classification, structured data extraction Integrations with Azure OpenAI / OpenAI API, FastAPI backends, and vector stores Vision-language and OCR-based extraction pipelines I care about shipping things that actually reduce manual work and hold up in production — not just demos. Happy to start with a short paid trial task so you can see the quality of my work before committing to a larger engagement. Let's talk about what you're trying to build. Skills (tags to add on Upwork) Generative AI, LLM, RAG (Retrieval-Augmented Generation), LangChain, LangGraph, Agentic AI, Prompt Engineering, Azure OpenAI, GPT-4o, Function Calling, Vector Databases, FAISS, Neo4j, GraphRAG, Semantic Search, FastAPI, Python, Document AI, OCR, Computer Vision, Hugging Face Transformers, PyTorch, Machine Learning, PostgreSQL, Databricks, Docker Portfolio / Project entries to add 1. RAG-Based Technical Document Compliance Checker FastAPI · Azure OpenAI · FAISS · Azure Blob · Databricks Built a RAG system that evaluates technical documents against a 5,000+ rule policy knowledge base, cutting manual review time by 70% with 92% violation-detection accuracy. Extended into a Graph RAG + Vector RAG hybrid multi-agent architecture (Neo4j + LangGraph) for multi-hop reasoning over relationship-heavy compliance queries. 2. NC Ticket Summarization & Classification Azure OpenAI · FastAPI · PostgreSQL · Databricks Jobs Automated non-conformance ticket summarization and multi-class classification via prompt engineering, deployed as a daily Databricks job, reducing manual triage effort by 80%. 3. LCO Patent Assist — Patent Analysis Tool Azure OpenAI · Azure Document Intelligence · OpenCV · DOCX Processing Hybrid patent analysis tool combining OCR, rule-based parsing, and GPT-4o for structured extraction of claims, descriptions, and figures from patents, with intra-document similarity search for claim-to-description mapping. 4. Warehouse Path Optimization & Analytics TSP · OpenCV · Python · Heatmap Analytics TSP-based path optimization for warehouse picking, reducing average path length by 25%, with heatmap tracking of high-traffic zones.

Experienced in building scalable real-time video intelligence systems — from traffic analytics to sports performance tracking, OCR, Speech Processing, and LLMs. With 5 years of expertise in real-time video analytics, document automation, and AI-driven insights, I leverage top technologies like Pytorch, TensorFlow, Deepstream, OpenCV, DeepSpeech, and Hugging Face to deliver scalable, intelligent systems. Let’s transform your vision into reality! 🚀 🔧 Tech Stack : 💻 Computer Vision and Video Analytics 🔹 OpenCV 🔹 TensorFlow 🔹 PyTorch 🔹 YOLO (You Only Look Once) 🔹 MMPose (Pose Estimation) 🔹 GStreamer (Video Processing) 📄 OCR and Document Processing 🔹 Tesseract OCR 🔹 EasyOCR 🔹 Pytesseract 🔹 Google Cloud Vision API 🔹 AWS Textract 🤖 RAG and LLMs (Large Language Models) 🔹 OpenAI GPT-3/4 🔹 Hugging Face Transformers 🔹 LangChain 🔹 Pinecone (Vector Database) 🔹 LLamaIndex 🔹 Ray (Distributed Computing for LLMs) 🎤 Speech Processing and Speech-to-Text 🔹 Google Speech-to-Text 🔹 Amazon Transcribe 🔹 Microsoft Azure Speech Service 🔹 DeepSpeech (Mozilla) 🔹 Coqui 🔹 Whisper (OpenAI) ⚙️ Deep Learning & Hardware Acceleration 🔹 CUDA (GPU Acceleration) 🔹 TensorRT 🔹 NVIDIA DeepStream SDK 🔹 OpenVINO 🔹 Jetson Nano (Edge Computing) 🔹 EdgeTPU 🌐 Cloud, Deployment, and DevOps 🔹 Docker 🔹 Kubernetes 🔹 AWS S3 🔹 GCP AI Platform 🔹 Jenkins 🛠️ Previous Projects : 1. AI-Powered Smart City Traffic Management System 🚦🚘 2. Smart Factory Monitoring and Safety System 🏭🚧 3. Voice-Activated Medical Transcription System 🩺📝 4. Multimodal Document Understanding and Automation 📄🤖 5. Personalized Virtual Assistant for Customer Support 🎙️💬 6. Real-Time Sports Analytics and Player Performance Tracker ⚽📊 7. Smart Home Surveillance and Intruder Detection 🏡🎥 8. AI-Powered Healthcare Data Extraction and Analysis 🏥📈 9. AI-Driven Financial Document Automation 💼📑 10. Real-Time Video Surveillance for Compliance in Factories 🎥🏭 🚀 Let’s Build the Future Together! With my extensive experience in deploying AI-driven solutions across multiple domains, I'm ready to take your projects to the next level. From Computer Vision to LLMs and OCR, I bring a passion for innovative technology and a track record of delivering high-impact solutions. Let’s transform your ideas into reality and drive success together!

With 7+ years of experience in AI/ML, I focus on building solutions that are not just technically sound but also practical and valuable in real-world scenarios. My work is driven by research, experimentation, and selecting the right technologies for each unique problem. 🔹 Where I Add Value I have strong hands-on experience in Computer Vision / Machine Vision, working on problems such as: * Object detection and recognition * Multi-camera tracking and digital twin systems * Face recognition and human pose estimation * Edge AI and real-time inference * Inspection systems and anomaly detection * OCR and text extraction * Data preparation including segmentation, augmentation, and synthesis 🔹 Machine Learning Expertise Depending on the problem, I apply a wide range of ML techniques: * Supervised Learning: Classification, Regression * Unsupervised Learning: Clustering, Dimensionality Reduction * Semi-supervised learning * Reinforcement learning 🔹 NLP & AI Systems Alongside vision, I’ve worked on intelligent systems involving: * GPT-based models (GPT-3, GPT-4) and LangChain workflows * Text summarization and content generation * Recommendation systems (feature-based, user-based, hybrid) * Sentence similarity and semantic analysis * Conversational AI and dialog systems * Speech processing (ASR, speech synthesis) * Machine translation 🔹 Deep Learning Applications I’ve applied deep learning across multiple real-world use cases: * Multi-camera tracking systems * Autonomous drones * Chatbots and service bots * Predictive analytics solutions I’ve also worked closely with startups and businesses to build MVPs and POCs, helping them validate ideas and move faster toward production. ✔️ Open to signing NDAs for confidential projects ✔️ Additional demos and project details available on request If you’re looking to build something in AI or want to explore a new idea, feel free to reach out happy to discuss and contribute. Best regards Disha