AI Product Manager · Sydney, Australia

Istartedwithcode.
I stayed for building.

AI Product Manager with an engineer's hands. I shipped fullstack products to 50M+ users, then moved to deciding what to build. Now I do a Master's in AI at UNSW and build AI products end to end. I care as much about whether a thing is worth building as whether it works.

ex-PM @ RekroMS AI @ UNSWStartmate Founder Fellowex-Bewakoof · 50M users
RAGLLM evalsAgentsTool-callingMultimodalEmbeddingsNext.jsTypeScriptProduct strategyPRDsExperimentspgvector
01Why I build

Engineering was the door, not the room.

I've wanted to build things for as long as I can remember, first with code, then with product, startups, and AI.

Early ambition

I grew up in Bangalore, where it felt like everyone was building something. I wanted something of my own before I really knew what that meant.

What changed

I tried to start a company before I graduated: an “Uber for trucks” for small and mid-size factories. YC rejected it. It made their top 10% of rejections, which I've decided to count as an encouraging signal. Mostly it was the first time I thought past the code to the actual problem.

Where I'm going

I moved to Sydney for a master's in AI at UNSW, mostly to see where the technology was heading. I got pulled into the founder world: a Startmate Founder Fellowship, the Peter Farrell Cup pitch competition, late nights at UNSW Founders. Humbling, in a useful way.

02Projects

Four AI products, built end to end.

Each ships a working demo, an engineering case study, and a product case study. Every demo runs in mock mode, so it works with no API keys.

Evaluation / LLMOpsMock demo

AgentEval Studio

An evaluation and observability workbench that compares AI prompt / RAG / agent variants on quality, cost, latency, and failure modes, and recommends a release gate.

AI EngineeringAI Product Management
Next.jsTypeScriptAnthropic APILLM-as-judge
RAG / Product StrategyMock demo

SignalDesk AI

An AI product-intelligence workspace that ingests user feedback, clusters pain points, finds evidence, and generates PRDs, roadmap bets, and experiment plans, every claim cited.

AI EngineeringAI Product Management
Next.jsTypeScriptAnthropic APIOpenAI embeddings
Multimodal / Product UXMock demo

ScreenSense QA

A multimodal UX/product QA tool that reviews UI screenshots for accessibility, friction, copy clarity, and visual hierarchy, and returns prioritised, severity-scored recommendations.

AI EngineeringAI Product Management
Next.jsTypeScriptClaude vision (claude-opus-4-8)Structured output
Agents / Trust & SafetyMock demo

WorkflowPilot Safe Agents

A safe-agent demo that turns a business goal into a proposed multi-step workflow, runs only human-approved tool calls, and records every action in an audit trail.

AI EngineeringAI Product Management
Next.jsTypeScriptClaude tool-useHuman-in-the-loop
03Water

Confidence comes before skill, not after.

Diving in the Andamans, teaching kids to swim in Sydney. The water taught me more about learning, patience, and trust than most things at work.

Confidence changes everything. In water, and out of it.

Building something? Let's talk.

I'm JP, open to AI engineering and product roles, and to people building interesting things.