Rishab Hanjagimutt

Projects

I build to learn. Each of these started as a real problem I wanted to solve — and became a lesson in making product decisions under constraint.

UltimateMe

iOS · Health

AI health coaching app that connects wearable data to personalized guidance.

Problem

Existing health apps surface data but don't do anything useful with it. Your watch knows you slept poorly and skipped the gym — but it never connects those dots or tells you what to do next. There's a gap between data collection and actionable coaching.

What I Built

A native iOS app that reads from HealthKit — sleep, activity, heart rate, HRV — and pipes that context into Gemini AI to generate personalized coaching responses. Cloud sync via Supabase, GDPR-compliant data handling, and 57 unit tests covering the core coaching logic.

Key Decision

I chose Supabase over local-only storage early on, even though local would have been faster to ship. The reasoning: cross-device sync and any future social or sharing features would require a cloud layer. Building that foundation later would have meant re-architecting around user data — painful and risky in a health context.

What I Learned

Shipping a regulated-adjacent health product means data privacy isn't a feature you add later — it's an architectural constraint you design around from day one. Every schema decision, every permission prompt, every sync event has compliance implications. I learned to think about privacy the way I think about quality in MedTech: it has to be built in, not bolted on.

Swift SwiftUI HealthKit Google Gemini AI Supabase iOS 18+

Spectrace

AI · MedTech

AI-powered OCR pipeline that extracts structured data from engineering drawings.

Problem

In MedTech manufacturing, engineers spend significant time manually extracting data from engineering drawings to build traceability matrices. It's tedious, error-prone, and a real bottleneck — especially when drawing packages span hundreds of pages across multiple revisions.

What I Built

A modular pipeline using PaddleOCR for initial text extraction, followed by a Groq Vision LLM validation layer that interprets the structured output in context. The result is a clean traceability matrix — exported as structured data — surfaced through a React frontend. Deployed serverlessly on Modal so it scales without managing infrastructure.

Key Decision

The first version used OCR alone. Results were inconsistent — especially on complex drawings with tolerance callouts, revision tables, and non-standard fonts. I added a two-step OCR + LLM validation layer after seeing how often single-model outputs misread domain-specific notation. The extra step added latency but dramatically improved precision on exactly the fields that matter for traceability.

What I Learned

LLM validation on top of traditional OCR is a pattern worth knowing. For domain-specific documents — engineering drawings, clinical forms, regulatory submissions — a second model that understands context catches what raw OCR misses. The combination is more robust than either alone.

Python PaddleOCR Groq Vision API React TypeScript Modal

Congressional Trade Tracker

Automation · Civic

Automated monitor that surfaces congressional financial disclosures in real time.

Problem

Congressional trading disclosures are legally required to be public — but they're buried in PDFs on government websites, filed inconsistently, and effectively inaccessible to anyone who isn't actively watching. The transparency exists on paper, but not in practice.

What I Built

A Python bot that scrapes disclosure PDFs on a schedule, parses the trade data, stores it in SQLite, and fires formatted alerts to Discord in real time whenever new trades are detected. Tracks multiple politicians simultaneously and handles deduplication across runs.

Key Decision

I chose Discord over email for delivery — not for technical reasons, but for distribution ones. The community of people who care about this data already lives in Discord servers. Meeting users where they are, rather than asking them to check a dashboard or subscribe to a newsletter, turned out to be the most important product decision I made.

What I Learned

Distribution strategy matters as much as the product itself. I spent more time on the parsing logic than the delivery mechanism — but the Discord integration drove engagement more than any feature I added. The lesson: figure out where your users already are and bring the product to them, not the other way around.

Python SQLite Discord API PDF parsing

Experience

May 2024 — Present

Paragon Medical

Chicago, IL · AMETEK

Quality Engineering Manager

Strategic leadership across 10 global medical device and combination-product sites, directing a team of 30 including supervisors and engineers.
Generated $20M in incremental revenue through commercial negotiations and ensuring product capabilities met customer and market requirements.
Leading post-acquisition integration of 3 sites, with goals targeting $70M in pipeline opportunities.
Harmonized quality and business systems across 7 sites, accelerating product development by 20% while maintaining FDA 21 CFR 820 and ISO 13485 compliance.
Served as strategic advisor to executive leadership on M&A diligence — financial modeling, competitive positioning, and quality risk evaluation for 2 acquisition targets.
Transformed the NPD and Design Control framework, increasing product launch success rates by 15%.

Oct 2020 — May 2024

Medtronic

Plymouth, MN

Senior Engineering Supervisor

Led a team of 8 engineers, driving the team to exceed KPIs by 35%.
Created and executed an innovation strategy generating $5M in annual savings.
Led Design Transfer Remediation for legacy products, reducing COGS by $8M YoY and increasing margin in line with global objectives.
Secured $1M in executive-level capital funding through constructed and presented business cases.

Engineering Supervisor

Directed manufacturing strategy for Nitinol and stainless-steel stent fabrication — 50% defect reduction and $1M in annual savings.
LEAN transformations and process optimization resulting in $1.5M savings YoY.

Quality Engineer

Spearheaded validations and process improvements (DVT, V&V, FMEA, IQ/OQ/PQ), achieving a 600% increase in production and 15% market share gain.

Dec 2024

University of Minnesota

MBA — Carlson School of Management

Strategy, operations, and organizational leadership

May 2020

University of Minnesota

BS — Biomedical Engineering

College of Science and Engineering · LEAN Six Sigma Green Belt

RishabHanjagimutt

UltimateMe

Spectrace

Congressional Trade Tracker

Let's connect.

Rishab
Hanjagimutt