I build AI-native products end to end—from model adaptation and low-latency inference to native apps, backend systems, testing, and production release.
Nearly five years in production engineering, including 0→1 products and consumer systems used by millions.
On-device LLMs · Native iOS, macOS & Android · Production systems
I built and shipped a production macOS autocomplete system around OLMo 2 1B—adapted, evaluated, optimized, signed, notarized, and delivered end to end.
Blinded 200-case evaluation · LoRA across all 16 transformer layers
Applied AI is not about putting a model everywhere. It is knowing which parts must stay deterministic, where generation adds value, and how the whole product remains dependable.
Built end to end across Flutter iOS and Android clients, Supabase and PostgreSQL backend services, and Vertex AI and Gemini workflows, with authentication, realtime data, subscriptions, push notifications, localization, and production delivery.
Region-aware fallbacks · bounded retries · malformed-JSON recovery · token/cost observability
I designed explicit precedence for calls and messages, keeping decisions local, reviewable, and fail-safe.
5-second call-screening window · 5-minute repeat-caller safeguard · 10 SMS categories
Before applied AI, I learned to ship inside platform constraints, sensitive workflows, consumer scale, security reviews, partial failures, and release pressure. That foundation still shapes every system I build.
Olly · 2023—2025
As one of two frontend engineers in a five-person international team, I owned iOS delivery through App Store launch and sustained releases.
Read the Olly case studyRailYatri & IntrCity · 2021—2023
Across five production apps, I modernized architecture, improved reliability, remediated security findings, and led two developers while remaining hands-on.
Read the RailYatri case studyBuilt substantial TypeScript and React frontend work for engineering metrics, AI-generated insights, team and project views, and delivery signals. Partnered with backend engineers on API contracts, data models, and product behavior.
Resolved recurring ANRs, crashes, runtime errors, slow interactions, and reliability failures. Rebuilt several ANR-prone WebView paths as native Flutter flows and added Firebase production instrumentation and analytics.
A career built around ownership under constraint.
Applied AI & Consumer Products
Building SpellType, Cosmicly, and NoRing—products spanning model adaptation and evaluation, on-device inference, production LLM workflows, native clients, backend systems, testing, and release delivery.
Shuru Technologies
Delivered 0→1 native iOS healthcare workflows, data-heavy TypeScript and React product experiences, and production reliability work in a Flutter point-of-sale application.
RailYatri (Stelling Technologies)
Worked across five production Android applications on architecture modernization, reliability, security remediation, testing, releases, and hands-on technical leadership.
Bachelor of Technology in Computer Science EngineeringJaypee Institute of Information Technology (JIIT), Noida
“Consumer scale and security, sensitive native workflows, then AI-native products spanning models, applications, infrastructure, and release.”
Judgment across the whole system.
I’m based in India and open to relocation and suitable global-remote roles where applied AI, native product engineering, and end-to-end ownership meet.