Muhammad Ahsaan Ullah
AI Systems Engineer | Python/FastAPI · Agentic AI · RAG
BS Computer Science Graduate, University of Management and Technology, Lahore
Based in Pakistan. Available for remote engineering & workflow automation projects worldwide. Building reliable systems that reduce repetitive manual work across messages, documents, APIs, and internal operations.
Engineering Philosophy
I build end-to-end AI applications with practical software-engineering foundations: typed APIs, data validation, authentication and tenant isolation, asynchronous workflows, retrieval/evaluation pipelines, testing, containerization, and deployment.
Every system is engineered with clear architectural boundaries: tenant-isolated PostgreSQL architectures using Row Level Security (RLS), asynchronous FastAPI microservices, deterministic agent execution loops, and automated test coverage.
Working Tools. In Production.
Tools I use daily to build production systems: a battle-tested working stack, not a checklist.
Backend & Cloud
Multi-cloud & Backends
AI & Vector Engines
Agents, RAG & Vision
Auth, Voice & APIs
Real-time & Voice AI
Web & Desktop
Client Platforms
Portfolio
Featured Projects
Live systems engineered with production discipline, automated testing, and strict architecture.
Voice-assisted field service dispatch for HVAC and plumbing operations. Combines ElevenLabs voice AI, authenticated n8n workflows, Cloudflare Workers with SQLite Durable Objects, and an operations dashboard.
Self-hostable, evidence-backed candidate resume screening workspace for HR teams. Generates 100-point job rubrics, auto-redacts PII, scores CVs with verbatim quotes, and enforces human-in-the-loop decisions with prompt-injection defense.
Locally deployed Windows AI agent built with LangGraph for web research, file operations, terminal execution, and workflows, featuring strict Human-in-the-Loop approval gates and 68 automated tests.
A multi-tenant RAG application designed for source-grounded document Q&A using hybrid retrieval, reranking, verifiable page-level citations, and 55 automated unit/regression tests.
Private-beta multi-tenant restaurant SaaS turning WhatsApp orders into structured kitchen/POS operations using FastAPI, React, PostgreSQL RLS tenant isolation, Roman Urdu parsing, and 32 tests.
Ultra-lightweight Windows desktop companion: floating animated pet (Fluffy Star) with hydration/chai-break alerts and an instant-summon infinite whiteboard canvas with local atomic persistence.
Offline-first Windows desktop POS for Pakistani mithai & bakery shops. Shipped as an Electron shell bundling portable PHP 8.4 and Laravel 11 with SQLite, supporting fractional weight/piece billing, daily FIFO batch inventory, and Z-Reports.
DeepFakeShield
Computer Vision FYPComputer Vision Final Year Project for classifying media as Real, Deepfake, or AI-Generated using PyTorch CNNs, FastAPI inference, and frame analysis (95.83% XceptionNet-41 accuracy on a balanced image holdout).
B2B e-invoicing application designed around ZATCA-oriented compliance workflows at exportshieldpro.online, with ECDSA PKI signing, XML/UBL validation, and sandbox integration.
Timeline
Experience
Architected and deployed AI systems, agentic automation pipelines, and asynchronous backend platforms for contract clients and independent SaaS deployments:
- DispatchAI (GitHub): Voice-assisted field dispatch system with ElevenLabs AI, authenticated n8n workflows, Cloudflare Workers, SQLite Durable Objects, and 149 automated tests.
- ScreenOS (GitHub): Self-hostable, evidence-backed candidate resume screening workspace with 100-pt rubrics, PII redaction, prompt-injection defense, and 79 automated tests.
- Agent Friday (GitHub): Locally deployed Windows AI agent using LangGraph state machines, terminal execution, and human-in-the-loop safety gates (68 tests).
- Waraq AI (waraqai.netlify.app): Deployed multi-tenant hybrid RAG system with verifiable page-level citations and 55 automated tests.
- TarkaBot (tarkabot.online): Private-beta multi-tenant Restaurant SaaS automating WhatsApp orders, kitchen KDS, and delivery dispatch with PostgreSQL RLS.
- PeepDesk (GitHub): Ultra-lightweight Windows desktop companion featuring animated desktop pet (Fluffy Star), hydration alerts, and infinite canvas with local atomic storage.
- Macaron POS (GitHub): Offline-first Windows desktop POS for bakeries bundling portable PHP 8.4 and Laravel 11 in Electron with SQLite, FIFO batch allocation, and 60 automated tests.
- DeepFakeShield: Computer Vision FYP for synthetic media classification achieving 95.83% XceptionNet-41 accuracy on a balanced image holdout.
- ExportShield Pro (exportshieldpro.online): ZATCA-oriented e-invoicing middleware with cryptographic ECDSA PKI signing and XML/UBL validation tested in the ZATCA sandbox.
Built Power BI analytical dashboards and complex SQL queries; automated recurring reporting pipelines and data extraction workflows.
Built ML and NLP models in Python; created interactive Streamlit dashboards to validate model results and streamline evaluation workflows.
Carried out data cleaning, exploratory data analysis (EDA), and feature engineering pipelines for predictive modeling.
Background
Education & Certifications
BS Computer Science
University of Management and Technology (UMT), Lahore