Awais Nazir
Islamabad, PakistanI build the systems behind the interface: APIs, databases, and AI tools that turn complex problems into useful software.
AI RAG System Production-Ready Document Intelligence Backend
Register, log in, and manage their own document library · Upload PDF, DOCX, and TXT files (up to 50MB per file) · View, organize, and delete uploaded documents · Chat with their documents using natural language
A facial recognition backend built for a Fiverr client, deployed across Windows, Linux, and Jetson edge devices.
Built and deployed the integration backend across Windows, Linux, and Jetson ARM64. · Tracked down and fixed platform-specific issues along the way, · including a GStreamer incompatibility on Jetson and SDK lock contention bugs that were causing instability.
An AI chat assistant for Hisab Kitab that helps users log expenses, check balances, and manage udhar safely through a confirm-before-save flow.
I built a FastAPI-based AI agent that connects the Hisab Kitab app with OpenAI and the existing Hisab API. · The agent can understand Roman Urdu and English messages, fetch user-specific data, propose expenses, settlements, and udhar entries, and return a pending action card for the frontend to show. · The key safety feature is the propose-confirm flow: the AI prepares the action, but the user must click Confirm before anything is saved. I also added persistent chat sessions, pending action storage, per-user scoping, protected API routes, run logging, and eval tests to measure accuracy.
From Python projects to production services. A few places where I’ve put the tools into practice.
Working on production backend systems: real-time notifications through WebSockets and SendGrid, file upload pipelines, and deployments on AWS.
Python
Docker
NestJS
FastAPI
PostgreSQL
AWSHiring for your team or have a project in mind? Tell me what you’re building.
uetawais42@gmail.comMore ways to connect
