Production agents
built and owned end to end.

Started not as a software engineer but as a researcher solving a genuinely hard spatial perception problem for a space mission. Mono vision depth detection — making a rover navigate a lunar environment using a single camera — is not a trivial problem. It requires understanding geometry, uncertainty, and edge cases.

Signal: Thinking about AI as a tool for solving hard real-world problems before most people were using the word 'AI' in their job titles. The origin of the computer vision seed.

Immediately after research, went hands-on with production software building a food delivery platform, order processing, and bulk automation with Java, Spring, MySQL. Not glamorous — but important.

Signal: The full-stack foundation. Understanding systems end to end — databases, APIs, business logic, infrastructure. Java, Spring and MySQL in production; the layer beneath everything built since.

Delivering AI solutions across wildly different industries — automotive (TVS Motors), retail (Target), aerospace (Airbus), logistics (Volvo), fintech (Varthana), payments (Walmart/PhonePe). Delivered a workshop at ODSC (Open Data Science Conference) on implementing AI and deep learning in enterprise environments, training 100+ professionals.

Signal: Learned how AI lands — or fails to land — in real enterprise contexts. The diagnostic instinct starts here: 'what problem are you actually trying to solve?' before proposing a solution.

Built a company merging AI/AR virtual try-on engines and an NLP-driven visual RAG search system. Embedded on the floor with retail clients, watched how their staff actually behaved, and prototyped in client sessions.

Signal: Leading people and building systems simultaneously. Translating a customer's floor-level problem into a technical architecture with real stakes.

Owned the full technical direction. Built a Designer AI Assistant using RAG over design documents, and a manufacturing lifecycle platform. Researched Gaussian Splatting and PyTorch3D and made the call to integrate an API rather than build from scratch.

Signal: Technical roadmap ownership. Pragmatic trade-offs and shipping systems. Knowing when NOT to build is as valuable as knowing how to build.

Deployed multi-agent orchestration, LLM inferencing, memory systems, RAG pipelines, observability, MLOps, and CI/CD. Reduced token usage by 10x through prompt optimisation and caching, and improved agent efficiency 3x (60s to 20s) on the core workout calibration feature. Put 100% safe guardrails in a high-stakes application.

Signal: Operating at the production edge of agentic AI. Applying the consulting diagnostic instinct to observability data to advise a go-to-market pivot.

Inherited a Flutter + GCP platform in critical-failure alpha. Built a guard-railing and validation layer across Vertex AI integrations, eliminated 100% of AI crash failures, cut latency by 55% (15s to 7s), and conducted a GDPR/AI Act compliance audit.

Signal: Breadth of production AI experience—greenfield build, iterative product development, and rescue engineering in regulated environments.

Shipped five live production systems independently: a hosted multi-agent platform that turns a described business intent into a working, deployed prototype in under a minute (Protash), an infrastructure tool solving the token cost of file browsing (Nexus-MCP), an end-to-end agentic application pipeline (JobScout), a multi-agent canvas orchestrator (AI Mood Board), and a 3-agent curriculum-to-content pipeline with a two-layer evaluation framework (CR8).

Signal: Alongside client work, I ship. Five live production systems built independently — proving continuous, hands-on building at the production edge of agentic AI.

Shipped on the organisation's Terraform/Terragrunt, GitHub Actions and Argo CD deployment stack, and set up Okta SCIM/OIDC authentication with admin/user group management for the tooling I built. Modelled incident.io, Jira, Datadog and GitHub data into governed, OKR-level Snowflake metrics, and built the AI Hub on top — a full-stack engineering dashboard unifying GitHub, Jira, Claude and Codex telemetry into one view of how AI was actually being used.

Signal: Tied every metric to an owner and an outcome — a dashboard is only useful once a team can act on it against its own goals. The same embedded, end-to-end ownership motion I had previously applied on client sites, now applied internally.