Hammad Ur Rehman

AI Engineer · Islamabad, Pakistan

Hammad Ur Rehman, AI Engineer

Hammad Ur Rehman

I build systems that read thousands of documents so people don’t have to.

A year shipping production AI at AIVSTUDIOS: pipelines for legal record building, clinical summarization, and platforms that run themselves.

See the work Get in touch
Year shipping production AI
1+
Systems built and delivered
15+
Global, Agentic Legal RAG Challenge
26th
Domains worked in
4

01Selected projects

Systems, not demos.

Every project below runs against real data for real users, across legal, healthcare, sports and commerce.

Flagship project

A pipeline that reads, sorts and rebuilds thousands of court documents

The problemLegal teams were manually collecting, reading and reformatting thousands of court PDFs into standardized records. Slow, repetitive, and easy to get wrong.

What I builtAn automation bot pulls the documents in. One agent reads each court decision, a second classifies it, then an automation layer handles the shrinking, standardizing, numbering, titling, splitting, duplicate checks, record building and bookmark generation.

Then the humans step inA custom PDF editor lets users refine any output, with agents behind it handling edits and rendering, plus automation for volume assembly, OCR and final flattening.

Lead developer · Python, Multi-agent LLM, OCR, PDF engine, Workflow automation

Production systemsShipped for clients and running live8

Legal

Weekly Legal Newsletter Engine

Runs every week once new court decisions land. Pulls case data across four departments, then agents build arguments, consolidate them and assemble a finished newsletter served over an API. Built end to end by me.

PythonFastAPIAgentsScheduling

appealmate.com

Legal

Appellate Argument Engine

Reads the record on appeal alongside the appellant and respondent briefs and the reply brief. One agent builds the supporting and counter arguments, a second consolidates them into a single line of reasoning, and a third drafts the questions a judge would put to each side.

PythonMulti-agent LLMLong-context RAGPDF

appellateshark.com

Health

Patient Records Summarizer

Users upload very large patient record PDFs; multiple agents condense them into short, organized summaries doctors and patients can actually read. I built a backend module of the pipeline.

OpenAIGeminiPythonPDF

acrodocz.com

Sports

Badminton Club Platform

Court assignment, live rankings and player statistics for clubs in Canada, with full authentication, AI-based player evaluation and an AI coach that guides players on what to work on next.

PythonAuthAI evaluationCoaching agent

smashlytics.net

Commerce

Commerce Platform with Live Ops

Shopping store backend and companion app showing real-time user activity and live ordering statistics as they happen.

BackendMobile appRealtime

Ops

Invoice Automation

An end-to-end invoice build-and-send flow as a multi-step, multi-zap workflow wired into ActiveCampaign and QuickBooks.

ZapierActiveCampaignQuickBooks

Legal

Court Record Builder

Automated record assembly for a US legal use case, sourcing case data through the CourtListener API.

PythonCourtListener API

Vision

Face-Recognition Attendance

Attendance system with live tracking built on AdaFace. It recognizes people as they arrive and logs it without anyone touching a device.

AdaFaceComputer visionPython

Independent buildsProducts started and finished on my own5

Independent

IntelliIntern

An internship platform where the testing, goal assignment and evaluation are all handled by AI, so companies can run a structured program without running it manually.

AI evaluationPythonWeb

Independent

Parkely

AI-driven parking management: allocation and day-to-day operations for parking spaces.

AIPython

Research and courseworkWhere the fundamentals were built2

Final-year project

RJ Assistant

A modular, privacy-first AI assistant that works online and offline. Understands voice and text commands for productivity, entertainment and system control, with local speech recognition and a local knowledge base so it keeps working without a connection.

FastAPIRasaWhisperVoskVector DB

Academic

ML Coursework Set

Bike-sharing demand prediction, spam email detection, house price estimation, an e-commerce recommender and customer churn prediction.

scikit-learnNumPyNLP

02ExpertiseDaily drivers

What I reach for.

Chosen for what ships and stays running, not for what’s new this month.

Languages & frameworks
PythonFastAPINext.jsFlutterSQLREST
AI & machine learning
Multi-agent systemsRAGNLPComputer visionDeep learningPrompt engineering
Models & agent tooling
OpenAIGeminiTransformersRasa
Speech & documents
WhisperVoskgTTSpyttsx3OCRPDF engineering
Data
PostgreSQLSQLiteVector databases
Automation & integrations
ZapierActiveCampaignQuickBooksCourtListenerWeb scraping

03ExperienceIslamabad, Pakistan

How I got here.

A year of production AI work on top of a computer science degree spent on machine learning, vision and automation.

Jul 2025 to Present

AI Engineer, AIVSTUDIOS

Building multi-agent pipelines and AI platforms for clients across legal, healthcare, sports and commerce. Lead developer on the document customization pipeline.

2025

Agentic Legal RAG Challenge

26th globally in the opening stage at over 80% accuracy; 57th globally in the final stage.

2021 to 2025

BS Computer Science

Machine learning, computer vision and automation throughout. Final-year project: RJ Assistant, an offline-capable AI assistant.

Certifications

  • Deep Learning Prerequisites: The NumPy Stack in Python (V2)Jan 2025
  • Python (Basic) Skill Certification, HackerRankJan 2025
  • Artificial Intelligence for Beginners, Simplilearn2024
  • Ongoing coursework in ML, NLP and AI applicationsContinuous

04QuestionsThe short answers

What people ask first.

The same handful of questions come up every time, so here they are answered plainly.

Who is Hammad Ur Rehman?
Hammad Ur Rehman is an AI Engineer and Python developer based in Islamabad, Pakistan. He builds multi-agent LLM systems, retrieval-augmented generation pipelines and large-scale document automation at AIVSTUDIOS, where he was promoted from Junior AI Engineer within six months. His production work spans legal technology, healthcare, sports management and e-commerce for clients in the United States and Canada.
What does Hammad Ur Rehman do as an AI engineer?
Hammad Ur Rehman designs and ships systems that read documents and produce finished work from them. He is the lead developer of a court PDF pipeline that processes thousands of documents through automated extraction, LLM-agent analysis of court decisions, classification, numbering, de-duplication, record building and bookmark generation, replacing a manual process that previously took hours per record. He also builds the backends and agent workflows behind legal newsletters, medical record summarization, badminton club management and e-commerce analytics.
What programming languages and frameworks does Hammad Ur Rehman use?
Hammad Ur Rehman works primarily in Python, using FastAPI for backend services, PostgreSQL and vector databases for storage, and Next.js and Flutter on the front end. His AI stack includes the OpenAI API, Google Gemini, Hugging Face Transformers and Rasa, with Whisper and Vosk for speech, AdaFace for face recognition, and OCR pipelines for document processing.
Is Hammad Ur Rehman a Python developer?
Yes. Python is Hammad Ur Rehman’s primary language and the one every production system in his portfolio is written in, from FastAPI services and multi-agent LLM orchestration to OCR and PDF processing pipelines, web scraping, and machine learning work with scikit-learn and NumPy.
What are multi-agent systems, and what has Hammad Ur Rehman built with them?
A multi-agent system splits a task across several specialised LLM agents that each handle one step and pass their output to the next. Hammad Ur Rehman has built several in production: an appellate engine where one agent constructs supporting and counter arguments from the record on appeal and the parties’ briefs, a second consolidates them, and a third drafts the questions a judge would ask; a weekly legal newsletter pipeline where agents build and consolidate arguments across four court departments; and a medical records pipeline where OpenAI and Gemini agents condense large patient PDFs into readable summaries.
Where is Hammad Ur Rehman based, and does he work remotely?
Hammad Ur Rehman is based in Islamabad, Pakistan, and works remotely with teams anywhere. His shipped projects have been delivered for clients in the United States and Canada.
How much experience does Hammad Ur Rehman have?
Hammad Ur Rehman has over a year of professional experience shipping production AI, beginning as a Junior AI Engineer at AIVSTUDIOS in June 2025 and being promoted to AI Engineer in December 2025. He holds a BS in Computer Science completed in 2025, and has delivered more than fifteen systems across four industries.
What has Hammad Ur Rehman been recognised for?
Hammad Ur Rehman ranked 26th globally in the opening stage of the Agentic Legal RAG Challenge at over 80% accuracy, and 57th globally in the final stage. He was also promoted from Junior AI Engineer to AI Engineer at AIVSTUDIOS within six months.
Is Hammad Ur Rehman available for hire or freelance work?
Yes. Hammad Ur Rehman is open to AI engineering and Python development work, and takes on projects involving multi-agent systems, LLM pipelines, RAG, document and PDF automation, and backend API development. He can be reached through the contact section of this site or on LinkedIn.
Which live projects can I see from Hammad Ur Rehman?
Several of Hammad Ur Rehman’s systems are publicly reachable: Appellate Shark (appellateshark.com) for appellate argument analysis, AppealMate (appealmate.com) for the weekly legal newsletter engine, AcroDocz (acrodocz.com) for medical record summarization, Smashlytics (smashlytics.net) for badminton club management, and two independent builds at wholesale.agenticstacksystem.com and freelanceagent.agenticstacksystem.com.

05ContactOpen to work

Got something worth automating?

Tell me what your team is doing by hand that a pipeline should be doing instead. I’ll tell you honestly whether it’s worth building.

Email

your.email@example.com

Phone

+92 306 9822189

Elsewhere

LinkedIn GitHub Résumé

Based in

Islamabad, Pakistan. Working with teams anywhere.