Open to full-stack & applied-AI roles

Full-stack platforms. Applied AI.

Ashwin Hingve —full-stack engineer.

I build and ship web platforms for e-commerce, matrimonial services and industrial IoT — owning architecture, development, integrations and deployment. I add applied-AI features with LLM APIs, tool calling, semantic search and OpenCV.

Bhopal, India · Remote & on-site · TypeScript · Next.js · Node.js · Applied AI

Selected work2024 — 2026
Smart ShaadiPre-launch
Next.jsAI assistantpgvector
WebSCADAFrontend live · backend offline
MQTTReactInfluxDB
PMStoreLive
Next.jsNode.jsPayments
See all projects
scroll

01 / ABOUT

One engineer, end to end.

PROFILE_01 ╌╌╌╌

Ashwin Hingve
Ashwin HingveFull-Stack Engineer · Bhopal, India

╌╌╌╌ ASHWIN HINGVE · IND

I'm a full-stack developer who owns projects end to end.

I translate client requirements into scoped applications and take them from architecture through development, integrations and deployment. My work spans e-commerce storefronts, a matrimonial platform and industrial IoT monitoring.

On the AI side I build practical features on top of LLM APIs — streaming assistants with tool calling and conversational memory, semantic search over embeddings, and OpenCV computer-vision pipelines. I use AI-assisted development heavily to ship quickly. Based in Bhopal, India; open to remote and on-site roles.

Client deliveryTypeScript · Next.js · Node.jsApplied AI · OpenCV

02 / WORK

Featured case studies.

Problem → contribution → implementation → current status. Each status reflects what's actually live, in testing, pre-launch or a demo.

01PRE-LAUNCHMatrimonial platform · Applied AI · 2026

Smart Shaadi

Problem

Matrimonial platforms match on filters, not on how two people actually communicate or whether their families align.

My contribution

I built the platform end to end — profiles, authentication, chat and payment integrations — and designed and wired its AI layer.

Implementation

  • Streaming, multi-turn assistant with conversational memory and read-only tool calling.
  • Provider-agnostic AI layer supporting Gemini and Claude.
  • Semantic profile re-ranking with embeddings in PostgreSQL / pgvector.
  • Conversation coaching, emotional scoring and experimental compatibility indicators.
Technical details

Semantic profile re-ranking uses 768-dimensional embeddings. Six user-facing AI features are wired end to end: a conversation coach, a sentiment-based emotional score, an experimental compatibility-risk indicator, family-values compatibility, the streaming assistant and semantic re-ranking. Further backend/admin models for churn risk, response-rate reputation, marriage-readiness and profile optimisation are implemented without a public UI.

Current status

Pre-launch: company registration is pending and the environment currently runs on dummy data and services ahead of commercial launch. The compatibility and risk indicators are experimental, not scientifically validated.

Next.jsFastAPIPostgreSQL / pgvectorGemini / ClaudeEmbeddingsTool calling
View beta
WebSCADA — SpaceAutoTech — Industrial IoT · WebSCADA
02BACKEND OFFLINEIndustrial IoT · WebSCADA · 2024–2026

WebSCADA — SpaceAutoTech

Problem

Industrial sites needed real-time device telemetry and browser-based monitoring without installing dedicated SCADA software.

My contribution

I developed the final WebSCADA implementation for SpaceAutoTech — telemetry ingestion and the browser-based monitoring dashboards.

Implementation

Device telemetry arrives over MQTT and is stored as time-series in InfluxDB, then surfaced through a React dashboard on a Node.js backend with device state, live dashboards and role-based access control.

Current status

The client-owned frontend remains accessible, but the backend is currently unavailable — so login and live data do not work. Shown for the implementation, not as a working demo.

MQTTNode.jsReactInfluxDBRBAC
View frontend
PMStore — Pharmacy e-commerce
03LIVEPharmacy e-commerce · 2026

PMStore

Problem

A pharmacy needed an online storefront where customers find medicines by composition and submit prescriptions, with full catalogue and order management behind it.

My contribution

I built and deployed the live website and its admin tooling, and developed the companion Android app.

Implementation

Medicine composition search, prescription upload, order management and catalogue import/export for bulk inventory — built on Next.js and Node.js with MongoDB / Mongoose, payment and order flows. The companion Android app uses Capacitor.

Current status

Live website. Capacitor Android app in Google Play testing, not yet publicly launched.

Next.jsNode.jsMongoDB / MongooseCapacitorPayments
Visit site

More projects

Additional client products and demonstrations.

TaptiFS — Food e-commerce

TaptiFS

LIVE

Food e-commerce

Live food & spices storefront built during the SpaceAutoTech engagement — authentication, Paytm payments, order tracking and a full admin dashboard.

Next.jsNode.jsPaytm
Visit site
Colonel's Pickle — E-commerce

Colonel's Pickle

LIVE

E-commerce

Live e-commerce site with ordering, authentication and an administration dashboard.

Next.jsNode.jsAuth
Visit site
Pulse Logic — Client demo · Web / Android / Desktop

Pulse Logic

CLIENT DEMO

Client demo · Web / Android / Desktop

A client demonstration across web, Android and desktop: an API-based chatbot focused on medical questions. Built as a demo — not a clinical or diagnostic tool.

Next.jsLLM APIsTauri
View demo
Marksman — Client demo · Web / Android

Marksman

CLIENT DEMO

Client demo · Web / Android

A client demonstration for web and Android: a shooting-focused AI coach with OpenCV target-hole detection and scoring.

ReactOpenCVReact Native
View demo
Gulaabi Clean — Home-service booking

Gulaabi Clean

IN TESTING

Home-service booking

A home-service booking product with separate customer and worker applications. Both apps are in testing ahead of public launch.

React NativeNode.js
Visit site
Deployment Corner — Hiring platform

Deployment Corner

LIVE

Hiring platform

A hiring platform with job listings, an applicant flow, a résumé builder and administration. Built during the SpaceAutoTech engagement.

Next.jsNode.js
Visit site

03 / EXPERIENCE

Where I've delivered.

May 2026 — PresentCurrent

Independent Full-Stack Developer

Dual Mind Labs

Translate client requirements into scoped applications and own frontend, backend, integrations and deployment across concurrent freelance projects.

  • Smart Shaadi · May–Sep 2026 · Pre-launchBuilt a near-complete matrimonial platform with profile matching, authentication, chat and payment integrations, plus a streaming AI assistant (tool calling, conversational memory) and semantic re-ranking on pgvector. Currently configured with dummy data ahead of commercial launch.
  • PMStore, Colonel's Pickle, Gulaabi CleanDelivered live PMStore and Colonel's Pickle e-commerce websites; built separate customer and worker apps for Gulaabi Clean's home-service booking (in testing).
  • Pulse Logic & Marksman · Client demonstrationsBuilt Pulse Logic (web/Android/desktop, API medical-questions chatbot) and Marksman (web/Android, shooting AI coach with OpenCV target-hole detection) as client demonstrations.
Nov 2024 — May 2025Nov 2025 — Apr 2026

Full-Stack Developer

SpaceAutoTech

Two engagements with the same company (with a break in between), delivering an industrial monitoring platform and client web products.

  • WebSCADADeveloped the final WebSCADA platform for device telemetry and browser-based monitoring using MQTT, Node.js, React and InfluxDB — including device state, dashboards and role-based access.
  • TaptiFSDelivered a live food e-commerce website with authentication, Paytm integration, order tracking and administration.
  • Deployment CornerDeveloped the hiring platform's job listings, applicant flow, résumé builder and administration.

04 / SKILLS

The toolkit.

Tools I've shipped with.

LANGUAGES

04
TypeScriptJavaScriptPythonSQL

WEB & BACKEND

09
ReactNext.jsTailwind CSSNode.jsExpressFastAPIREST APIsJWT / OAuthRBAC

DATA & AI

08
PostgreSQLpgvectorMongoDBRedisLLM APIs (Gemini / Claude)EmbeddingsTool callingOpenCV

DELIVERY

11
React NativeCapacitorTauriGitDockerLinux VPSNginxPM2VercelMQTTInfluxDB

05 / CONTACT

Let's work together.

I'm open to full-stack and applied-AI roles — remote or on-site — and to freelance projects.

If you're hiring or have something you want built, send a note with a few details and I'll get back to you.

RESPONSE TIME

Usually within 24 hours · IST

SEND A MESSAGE

Send directly from this page — no email app needed. Your details are processed by FormSubmit to email your message to me.