I'm Abdul Azeem — a backend engineer with 4+ years shipping production Python systems for fintech, accounting, and AI / LLM products. I've delivered 7+ live backends at Kavion.ai (Django, FastAPI, AWS Lambda) and built Invoize — a multi-tenant AI invoice extraction SaaS — end-to-end, solo.
Featured project: Invoize — multi-tenant AI invoice extraction SaaS, built solo (Django · Next.js · OpenAI · Mistral OCR · QuickBooks · Xero)
A production SaaS I designed and shipped end-to-end. Django / DRF backend with Fernet-encrypted credentials, Next.js / TypeScript frontend, an LLM extraction pipeline (Mistral OCR + OpenAI GPT-4o), and native QuickBooks Online + Xero OAuth integrations. Built solo over ~6 months alongside full-time work.
Mistral OCR reads the document (PDF, scan, phone photo, multi-page). OpenAI GPT-4o-mini converts it to structured JSON — vendor, invoice header, line items, tax, totals — with a confidence score on every extraction.
Native OAuth into QuickBooks Online and Xero. One click turns an extraction into a Bill against the right vendor and GL account. Sandbox and production environments both supported out of the box.
One platform, many client books. Admin manages credentials, quotas and branding centrally; each end-client gets their own portal, their own integrations, their own data — fully isolated.
Upload hundreds of invoices at once. Bulk-push reviewed extractions to QB / Xero in a single action. Vendor-alias memory means the second invoice from any supplier is fully automatic.
Not every firm pushes to an accounting platform. Download any extraction as Excel or JSON for spreadsheet workflows, audit trails, or downstream systems. Editable fields throughout — review & correct before exporting.
Your brand name, your logo, your domain. Fernet-encrypted credentials, JWT auth, per-client quotas, admin dashboards. Deploy on your AWS or use our managed hosting — same codebase either way.
Happy to share a code tour, architecture notes, or a live demo in an interview.
An AI-first stack tuned for shipping production-grade agentic products. Python backend, modern LLM tooling, cloud-native infra.
Multi-tenant SaaS architecture. REST APIs, async task pipelines, OAuth flows, encrypted credential storage.
LLM-powered extraction, RAG pipelines, and agentic workflows. Hosted APIs and local inference both in production use.
Type-safe React UIs end-to-end. Dark-mode design systems, responsive layouts, accessible flows.
Containerized deploys, Fernet-encrypted secrets, CI pipelines, AWS-hosted production workloads.
I'm Abdul Azeem, a backend engineer based in India with 4+ years of production Python experience. Currently a backend developer at Kavion.ai (N-Labs AI Pvt Ltd), where I've shipped 7+ production backends for fintech, accounting, edtech, and HR-tech — handling SAP, Razorpay, PhonePe, WhatsApp Business, and Stripe integrations end-to-end.
I specialise in multi-tenant SaaS, LLM-powered pipelines, and OAuth-heavy integrations. On the AI side I've shipped production code with OpenAI, Claude (Anthropic SDK), Mistral OCR, LangGraph, pgvector, and RAG. On the infra side: AWS Lambda microservices, Docker, GitHub Actions, Postgres at scale, Celery / Redis async pipelines.
My most recent solo build is Invoize — a full multi-tenant AI invoice SaaS with QuickBooks & Xero integration. I designed the architecture, the LLM extraction pipeline, the admin + client portals, the OAuth flows, and deployed the whole thing on Railway. It's the project I'm most proud of.
Currently open to senior backend / AI engineering roles — remote-first, India / UK / US time zones. Notice period: 30 days.
Looking for a backend engineer who can ship Python systems end-to-end and is genuinely comfortable across LLMs, OAuth integrations, and multi-tenant SaaS? Let's talk. Recruiter, founder, or hiring manager — happy to do a screen, code walkthrough, or live demo of Invoize.