National Exam Proctoring Analytics
10,000+ camera-scale monitoring workflows for exam operations.
Applied AI Systems Engineer
I turn AI prototypes into deployed systems.
Built large-scale mine video analytics, 10,000+ camera exam proctoring workflows, real-time CCTV intelligence, and multi-agent LLM products. Former Head CV Engineer now building agentic AI products with LangGraph, RAG, voice workflows, and multimodal pipelines.
Selected shipped work
A compact trail of agentic products, production computer vision, edge inference, and tools that moved beyond a demo screen.
Large-scale mine safety analytics across 7 deployed sites, with safety events, compliance alerts, dashboards, and edge/cloud monitoring.
A filesystem-centric multi-agent storybook pipeline with realtime streaming, generated illustrations, and print-ready PDF output.
A Socratic ideation tool that turns voice conversations into blogs, tweets, SCAMPER explorations, and product notes.
More production deployments
Additional shipped analytics work across exam operations, field safety, banking security, and industrial tracking.
10,000+ camera-scale monitoring workflows for exam operations.
Safety analytics for field environments, including hazard and compliance monitoring.
Security-focused video analytics for banking environments.
Wagon tracking and counting workflows for industrial operations.
Personal project
Where I can ship immediately
The throughline is production judgment: state, latency, artifacts, monitoring surfaces, field hardware, and interfaces that make AI behavior usable.
I build agent loops around real artifacts: files, PDFs, voice flows, RAG contexts, tools, and stateful workspaces.
LLM work spans RAG, fine-tuning patterns, structured outputs, guardrails, workflow design, and product UX.
I have shipped smart CCTV analytics, industrial monitoring, and edge inference across RPi, CPU, and GPU targets.
AI engineering stack
Contact signal
Useful when you need an agent product, LLM workflow, CV deployment, or prototype hardened into something people can use.
DeepSight AI Labs, independent AI products, industrial CV systems, and deployment history.
Public projects and experiments on GitHub.