Hi, I'm Parth.

AI Product Manager.
State Team Captain.
Coach.

From the product floor to the skating rink, building teams that deliver.

Live

Last commit · github_trending
Latest writing · The Mind We Raised in the Dark
Asked my AI this week · “What's PS AnalytIQ?”

updated by hand for now

I go looking for the problems nobody has owned yet.

The model is rarely the hard part of an AI product anymore; building has never been easier. The real work is judgment: choosing what to build at all, then wringing the most intelligence out of every token it costs to run. Five years in, that judgment is the thing I trust most. One problem is where I really felt it: PS AnalytIQ, the counterfeit-detection product I founded at PharmaSecure. The data had been hinting at fakes for months, one real code scanned thousands of times, and the win wasn't the algorithm so much as deciding exactly what to build around it. It runs in production now, catching fakes before they reach a patient, and it's the same instinct I bring to leading Product at uEngage today.

None of it started in an office. It started on a roller-hockey rink, where I spent more seasons falling than winning before I ever learned to lead a team to a national medal. I never really left it. I still play, I coach now too, and the kids I train have started bringing home national titles of their own. On weekends, I teach children their first lessons in a classroom. Sport and teaching gave me what no framework did: how to read a moment fast, commit before I'm certain, and carry people through the stretch when nothing works. The domains keep changing. The job never does.

It didn't start with job titles.

Five roles. One through-line: put AI to work.

May 2026 – now

AI Product & Experience Lead · uEngage

The kiosk was rewritten from the ground up and the enhanced version shipped inside a month. Kiosk GMV roughly doubled between May and August, and platform GMV grew about 13 percent over the same period.

See how I did it ›

uEngage powers ordering for more than 200 brands, from fine dining to quick service, bakeries, pizza chains, cloud kitchens and campus food, each with its own menus, rules and propositions. I own customer experience across App, Web, Kiosk and WhatsApp for all of them. The kiosk came first: one product carried end to end, from the feature set to the final screen.

What it taught meClarity ships faster than headcount. Decisions in writing, one build across the fleet, and a number behind every claim.

Read the full story ›

Sep 2024 – Apr 2026

Associate Product Manager · PharmaSecure

Founded PS AnalytIQ, the counterfeit intelligence layer now running on PharmaSecure's platform, which reduced the time to surface a suspect code by roughly 90 percent in testing.

See how I did it ›

A client kept returning to the same anomaly: single codes verified three thousand times. The answer was to stop interrogating codes individually and start interrogating the scanners behind them, using a hybrid of supervised and unsupervised models trained per manufacturer. That became PS AnalytIQ. I also drove a non-clonable technology programme end to end, from literature review to a prototype now in pilots, held the point of contact for the product authentication business, ran serialization for three of India's five largest pharmaceutical manufacturers, and built the company's inventory management system.

What it taught meThe model was the easy half. Pharma is rigorous about documentation and procedure, and that discipline is what makes trust auditable.

Read the full story ›

Aug 2022 – Aug 2024

Product Associate · CSIR-CSIO, Govt. of India

Built energy models that told identical machines apart with 99% accuracy, and ran a state-wide water audit that became a peer-reviewed Springer paper.

See how I did it ›

Two missions. Real-time water-quality monitoring for the Jal Jeevan Mission, including an audit of Punjab's water we ran from a lab we set up ourselves. And e-Sense, NILM energy models built with German research partners.

What it taught meThink in systems, not components. Sensors, algorithms, hardware and people only work when you understand how each piece talks to the rest. And once you own the whole process, impossible timelines become logistics.

Read the full story ›

2021 – 2022

Quality Automation, Analytics · Smart Energy Water

Went past writing test cases to improving the billing platform itself.

See how I did it ›

Quality automation for an analytics platform that bills a city's utilities. I didn't just document test cases, I improved the platform itself and kept its integrations honest.

2020 – 2021

ML Research Intern · DRDO

My first exposure to ML that had to work in the field, not in a notebook. The start of everything above.

Here's what that looks like when it ships.

Three problems, owned end to end.

Case 01 · uEngage · Food and beverage · 2026

Four channels. More than 200 brands. One platform.

Fine dining, quick service, bakeries, pizza chains, cloud kitchens, campus food. Every brand with its own menus, rules and propositions, and one owner for the customer experience across App, Web, Kiosk and WhatsApp.

The first success story

The kiosk, rewritten from the ground up in a month.

Carried end to end, from the feature set to every screen. We rebuilt the codebase and shipped the enhanced version inside a month. Live in mid-August, the entire fleet on one build three weeks later.

Measured like a product

Kiosk GMV roughly doubled, May to August.

79 tracked events and a weekly report that runs itself. Once a first item is in the cart, 84 percent of sessions pay.

Built for 200 brands

Configuration, not code.

Eighteen screens, six upselling screens configurable by brand, and a management dashboard: a brand's menu, offers, propositions, payment methods and theme change without an app release.

The other three channels

App, Web and WhatsApp, rebuilt from the journey up.

A KPI tree for the app, a specification for every post-order screen, the WhatsApp storefront re-read from the code, a loyalty programme designed for a national burger brand, and a cross-channel upselling engine in design. Platform GMV grew about 13 percent.

What it taught me

Clarity ships faster than headcount.

Decisions in writing, one build across the fleet, and a number behind every claim.

Read the full story ›

Case 02 · PharmaSecure · Pharmaceuticals · 2024–26

Find counterfeit medicines before they find patients.

Every pack carries a code a patient can verify to establish that the medicine is genuine. Most codes are never scanned at all.

The question a client kept asking

One code. Three thousand verifications.

Twenty on a single code already exceeds what a shelf and a customer can account for. Three thousand means one authentic code reproduced across a great many counterfeits.

The shift

Interrogate the scanner, not only the code.

A counterfeiting operation presents as a handful of devices moving through thousands of codes, in territories the genuine consignment never reached. So the system adjudicates the scanners first.

What I built

Rules a compliance officer can read, and a hybrid that learns two ways.

No labelled fraud existed, so the rules became the training data. A boosted tree ensemble learns the interactions they miss; an isolation forest registers what violates no rule at all. Every alert still carries its reasoning.

What it taught me

The model was the easy half.

Pharma is exacting about documentation and procedure, and that discipline is what makes trust auditable.

Read the full story ›

Parth with the IoT water-quality monitoring unit at the Ministry of Jal Shakti

Real-time pH, turbidity, conductivity, TDS

Jal Jeevan MissionDemo unit, Ministry of Jal Shakti

20 samples per districtOne month, our own lab

Punjab water auditThe dataset became a Springer paper

Told apart with 99% accuracy

e-SenseNILM electrical signatures

Ladakh, Roorkee, Jaipur

e-Sense hardwareLive appliance-level dashboard

Case 03 · CSIR-CSIO, Govt. of India · 2022–24

Make India's water and energy observable.

Under the Jal Jeevan Mission, the first IoT water-quality station in the tricity, streaming in real time.

The audit

Hundreds of samples. One month.

Labs quoted weeks and water doesn't wait. So we built the lab ourselves.

Energy

Three identical machines. Tell them apart.

e-Sense reads a building's whole electrical life from a single point. Our model told three same-batch air conditioners apart.

What it taught me

Think in systems, not components.

Read the full story ›

Parth in the Chandigarh jersey at the 61st National Roller Skating Championship

Silver at the NationalsAs captain of my state team, 61st Nationals, 2023.

The Chandigarh squad after the State Championship win

State ChampionshipWith the Chandigarh squad after the win.

Parth with the RHPL 2025 first runner-up cheque

RHPL 2025First runner-up, with the Hyderabad Heroes.

The wall at homeEvery medal has a season attached. Try the dots.

Parth playing pool at home in front of the medal wall

HomePool at home, in front of the medal wall.

Parth with four of his students wearing their medals

Back to the first rinkMy students now win national medals of their own.

Students with medals and a trophy at the nationals

National medals of their ownMy students at the national championships.

Young Chandigarh skaters at the nationals

The Chandigarh contingentSkaters I helped train, at the nationals.

“Captaincy: accountable for the outcome, but you don't take the shots. Your team does.”The best description of product leadership I know.

The rinkThe classroom ›

From relief drives to school admissions.

With the Harnoor Madhar Foundation: from COVID relief drives to getting the children of Jagatpura village into school, and keeping them there.

Parth reading with children in Jagatpura village — Teaching at the open-air classroom in Jagatpura.

Parth with schoolchildren — Weekend lessons at school.

Parth with children of Jagatpura village — With the children of Jagatpura.

A COVID relief drive — Where it began: relief drives, 2020.

“It's not how much you give, it's how much love you put into the giving.”The foundation's line. Ninety admissions is a number. The real product was trust.

AI is only worth it where it creates real value. My job is knowing exactly where.

Operationalize, don't decorate.

AI that ships inside a workflow beats a demo that impresses in a deck.

Automate execution, invest judgment.

Machines take the manual work; people move up to the calls only they can make.

Understand the model to place the bet.

Knowing how AI works tells you where it will pay off, and where it won't.

In the open

I build them to understand them.

The surest way I know to tell where AI pays off is to build with it myself. A few things I've been tinkering with off the clock, all public on GitHub.

A self-running weekly brief that ranks GitHub's trending repos by momentum, not lifetime stars, drops anything below a proven-star floor, then has an LLM explain each one in product terms: what it does, who it's for, and the week's theme. Built to answer a product question, not an engineering one.

deep_researchMulti-agent research · Python

Give it a topic and six small agents plan the searches, write a cited report, grade their own work, and re-research the weak spots before emailing the result. A compact, readable example of an agentic workflow with a self-correction loop and human-in-the-loop checkpoints.

rag-mfRAG pipeline · Python

A facts-only mutual-fund FAQ assistant, built in phases: it scrapes and normalises scheme pages, indexes them into Chroma with BGE embeddings, answers only from what it retrieves, refuses anything out of scope, and holds itself to a golden-set evaluation suite with daily re-indexing.

Everything I'm building ›

Research & writing

I write about AI, product & building teams.

A peer-reviewed paper, and essays on AI and product.

Peer-reviewed research

Combining clustering & ensemble learning for groundwater quality monitoring

Environmental Science and Pollution Research · Springer · 2025

The dataset behind it came from the Punjab groundwater audit I ran at CSIR-CSIO: hundreds of samples we collected and tested ourselves.

Read the paper ›

Also writing on LinkedIn

LinkedIn · Jul 2026 · 11 min

The Mind We Raised in the Dark

We built minds we couldn't look inside. Anthropic's interpretability research just switched the light on, and what it shows is worth sitting with.

Read article ›

LinkedIn · Jun 2026 · 10 min

The Girl Who Stopped Reading Her Own Homework

A Class 11 interview that rearranged how I think about AI guardrails. Users don't need protection, they need judgment.

Read article ›

Now

Fills itself every week.

Last commit

github_trendinga weekly brief that ranks trending repos by momentum

Latest writing

The Mind We Raised in the DarkLinkedIn · 11 min

Asked my AI this week

Let's build something.

Book a call parthkhungar33@gmail.com

Or just . It knows where my calendar is.

Chats with my AI are logged so I can improve it. Please don't share personal details.

AI Product Manager.State Team Captain.Coach.

The floor

The rink

I go looking for the problems nobody has owned yet.

Five roles. One through-line: put AI to work.

AI Product & Experience Lead · uEngage

Associate Product Manager · PharmaSecure

Product Associate · CSIR-CSIO, Govt. of India

Quality Automation, Analytics · Smart Energy Water

ML Research Intern · DRDO

Three problems, owned end to end.

Four channels. More than 200 brands. One platform.

The kiosk, rewritten from the ground up in a month.

Kiosk GMV roughly doubled, May to August.

Configuration, not code.

App, Web and WhatsApp, rebuilt from the journey up.

Clarity ships faster than headcount.

Find counterfeit medicines before they find patients.

One code. Three thousand verifications.

Interrogate the scanner, not only the code.

Rules a compliance officer can read, and a hybrid that learns two ways.

The model was the easy half.

Make India's water and energy observable.

Hundreds of samples. One month.

Three identical machines. Tell them apart.

Think in systems, not components.

From relief drives to school admissions.

AI is only worth it where it creates real value. My job is knowing exactly where.

Operationalize, don't decorate.

Automate execution, invest judgment.

Understand the model to place the bet.

I build them to understand them.

I write about AI, product & building teams.

Combining clustering & ensemble learning for groundwater quality monitoring

The Mind We Raised in the Dark

The Girl Who Stopped Reading Her Own Homework

Fills itself every week.

Let's build something.

That's the whole story.

AI Product Manager.
State Team Captain.
Coach.