Open to rolesResume

Mayur KarmakarFull-stack Applied AI Engineer

From interfaceto intelligence.I ship the whole system.

I build production products across React, Next.js, FastAPI, PostgreSQL, and Azure AI—turning document-heavy, high-stakes workflows into clear software people can inspect and trust.

Review selected work Open resume

Open to full-stack and applied AI rolesLinkedIn GitHub

Role

Full-stack + Applied AI

Experience

4+ years shipping products

Best fit

Complex workflows that need clarity

01 · Production evidence

Selected work

Recent applied AI systems first, followed by the earlier product work that built my full-stack, realtime, and domain experience.

Recent · 1

Applied AI document intelligence

AI Review Platform

zipp.ai ~ Oct 2025 - May 2026

A full-stack, AI-assisted document-review product that turns complex source material into structured, reviewer-ready insight.

What I delivered

Designed and delivered the end-to-end product across Next.js interfaces, FastAPI services, PostgreSQL, browser automation, and cloud AI integrations.
Built resilient ingestion and structured-processing workflows with validation, retry handling, persistence, and traceable outputs.
Delivered analytics surfaces with multidimensional exploration, comparative views, trend analysis, and reviewer-focused workflows.
Connected AI-generated outputs to source context, enabling faster inspection and higher-confidence human review.

Structured review

Recent · 2

Applied AI document intelligence

Document Review Workflow

zipp.ai ~ Oct 2025 - May 2026

An AI-assisted document-review workflow for turning complex operational records into structured, traceable reviewer insight.

What I delivered

Built OCR-backed document-processing flows that converted complex PDFs into structured, review-ready information.
Implemented validation and quality-check workflows that surfaced incomplete or inconsistent information for human follow-up.
Linked structured findings to source context, helping reviewers verify outputs quickly and confidently.
Delivered auditable review experiences and workflow support that improved traceability across document versions.

OCR and review

Earlier product systems

Expand for detail

Content2QuizBsecure - 2023 to 2025An AI-powered quiz generator for transforming text and uploaded files into structured question banks.

AI learning workflow

Question banks

Developed a Next.js, React, Drizzle ORM, and Tailwind application for quiz creation, review, and exam workflows.
Built OpenAI GPT flows that converted typed text and uploaded files into structured question banks.
Implemented RBAC, protected flows, exam scheduling, and automatic submission behavior.
Integrated PayPal and Stripe payments while keeping the content-generation UI responsive across devices.

Bsecure ProBsecure - 2023 to 2025A self-contained educational technology platform for online proctoring and exam management.

Online proctoring

Realtime integrity

Developed and deployed proctoring workflows using Next.js, React, Drizzle ORM, and Tailwind CSS.
Implemented live video and audio monitoring with WebRTC and OpenVidu, including screen recording and real-time violation alerts.
Built AI-based face and object detection flows to support exam integrity checks.
Integrated role-aware dashboards, live support chat, real-time messaging, and payment handling for proctoring operations.

Examd - CanvasBsecure / Wisteli - 2021 to 2025An online proctoring and exam management platform that integrates with LMS and test engines.

LMS integration

Canvas workflows

Revamped legacy exam and monitoring surfaces into clearer workflows for students, instructors, and proctors.
Implemented Canvas LMS assignment handling, configurable scheduling, countdown timers, auto-submission, and post-exam review.
Built real-time student-proctor communication using WebRTC, Socket.IO, and video/audio streaming.
Managed time-based exam windows, violation reporting, and LMS-compatible proctoring behavior.

CarelogiQWisteli - 2021 to 2023A HIPAA-compliant chronic disease management solution for value-based care teams.

Healthcare analytics

Clinical dashboards & Mobile App

Contributed to React and React Native healthcare workflows for chronic disease management.
Improved diagnosis preprocessing and clinical data visualization for care-team dashboards.
Designed responsive analytics views for patient vitals and healthcare trend interpretation.
Resolved platform-specific issues across Android and iOS that affected patient monitoring flows.

02 · Code in the open

Public builds

Two builds at different stages of my engineering path: a current claim-grounded AI workflow and an earlier forecasting experiment built from public vaccination data.

Featured applied AI project

Micro-Viva

An end-to-end application that processes assessment material and student submissions to generate claim-grounded viva questions.

Claim-grounded questions from assessment material and submissions
Retrieval workflows with LangChain, LangGraph, and pgvector
Structured LLM outputs with evaluation checks
SSE progress streaming and persistent generation state
Cloudflare Workers frontend and OVHcloud FastAPI backend
Nginx reverse proxy and custom-domain delivery

FFastAPILLangChainLLangGraphSSupabasePpgvectorSLStructured LLM outputs+4

Open live project

Experimental forecasting project

CowinHistory

A Django and React project that used historical vaccination-slot observations to estimate near-term availability.

Keras neural network trained on historical observations
Vaccination data collection and parsing workflows
Telegram integration
Center-level history and forecast presentation

React

Redux

React Router

Python

Django REST

MySQL+6

View code

03 · Architecture coverage

System stack

Organized by the part of the product it helps me own—not as a wall of logos. The stack supports the path from interface to model output and reliable delivery.

Layer 01

Applied AI workflows

Structured LLM pipelines, document extraction, RAG, and review experiences with source-level traceability.

AOAzure OpenAIGGPT-4.1ACAzure Content UnderstandingOOCRAAAzure AI SearchRRAG

Layer 02

Full-stack architecture

Typed product surfaces, API boundaries, persistence, and deployment-ready backend services.

Next.js

ReactFFastAPI

Node.jsPPostgreSQLRAREST APIs

Layer 03

Frontend systems

Component-driven development, state management, and performant interfaces for complex workflows.

Redux

Zustand

TanStack Query

Tailwind CSS

Shadcn

Framer Motion

Layer 04

Realtime and integrations

Live exam monitoring, communication flows, payments, auth, and third-party collaboration tools.

WebRTC

Socket.IOOOpenViduJJitsiZZoomCClerkSStripePPayPal

Layer 05

Cloud and delivery

CI/CD, containers, Azure hosting, and database platforms for shipping full-stack AI applications.

DDockerGAGitHub ActionsAAAzure App ServiceASAzure Static Web AppsVVercelSSupabaseNNeonTTurso

Layer 06

Data and ORMs

Practical data modeling, persistence, and review screens that keep AI output auditable.

Drizzle ORM

Prisma ORM

tRPC

Python

Django REST

Pandas

04 · Background

Foundation

The formal foundation behind the production experience, followed by focused learning that supported the stack I use today.

Degree

Bachelor of Computer Applications

Trident Academy Of Creative Technology, Bhubaneswar

August 2018 - September 2021CGPA 8.08

Supporting credentials

Continued learning

Formal learning that supports the production stack: React for modern interfaces, Python and Django for backend fluency.

Mar, 2021

React - The Complete Guide 2023

Udemy

UC-840177ec-c9f4-41f9-a39a-27d34e4af316

View certificate

Mar, 2018

Python and Django Full Stack Web Developer Bootcamp

Udemy

UC-ZPNYJ3TO

View certificate

05 · Next step

Let's find the right fit.

I'm open to full-stack and applied AI roles where I can own the interface, service layer, and the path from model output to a product people can trust.

Clear project notes help most

Timeline, users, documents, stack, and the current review bottleneck are enough to start a useful conversation.

Best fit

Applied AI applications, RAG and OCR workflows, React and Next.js interfaces, FastAPI services, and review dashboards.