A Flutter and Firebase app that dynamically prioritizes tasks using mood and energy metrics, with OCR-based note summarization and deadline extraction.
FlutterFirebaseML Kit OCR
About
I'm a software engineering graduate from NUST, where I finished as gold medalist with a 3.91 CGPA. Most of my research has been on EEG, classifying pathology in it and generating diagnostic reports from it.
I work on Arch Linux in Neovim and tmux, which is about as much of a setup as I want. Away from the keyboard I'm usually solving a cube, drawing, playing chess, or working through a maths problem.
Projects
A secure AI banking assistant built with a hybrid RAG pipeline, Qdrant, LangChain, and a fine-tuned Qwen2.5-3B model secured with NeMo Guardrails and Presidio.
PythonLLMsQdrantLangChainStreamlit
A hybrid deep learning pipeline integrating SCNet and VGG16 for seizure and pathological waveform detection, with a privacy-preserving LLM report generator using Qwen 3.
PythonFastAPIPyTorchReactDocker
A RAG-based therapy assistant built with TinyLlama and FAISS to support personalized, long-term memory across conversations.
PythonRAGLLMsFAISS
A microservices video platform on GCP: upload, transcode and stream, split across independently deployable services.
Express.jsGCPMongoDBNode.js
An e-commerce platform for rural women entrepreneurs to manage inventory and orders.
MERN StackGit
An IoT health wearable prototype with a Flask monitoring dashboard for real-time vitals and GPS location.
PythonFlaskEmbedded SystemsHTML/CSS/JSGit
A search engine indexing 150,000 NELA-GT 2022 articles with a retrieval pipeline based on token frequencies and barrel partitioning.
PythonReactFlaskGit
A centralized travel management platform: itineraries, bookings and vendors in one Django app.
PythonDjangoTailwindCSSHTML/CSS/JS
Experience
Software Engineer
Educative
Working on Educative's learning platform and Fenzo.ai using Flask, TypeScript, Google Cloud Platform, and LangChain.
FlaskTypeScriptGoogle Cloud PlatformLangChain
Deep Learning Research Intern
RheinMain University of Applied Sciences
Implemented the Stormer model and optimized global weather forecasting using latent ERA5 data. Devised a flood forecasting pipeline combining ERA5 weather data, river discharge maps, and Sentinel-1 satellite imagery.
Deep LearningWeather ForecastingERA5PyTorch
Teaching Assistant
National University of Sciences & Technology
Lectured on Git workflows and evaluated quizzes, assignments, and exams for a cohort of 90 students. Curated a HackerRank assignment with 5 algorithmic problems.
TeachingGitAlgorithms
Deep Learning Research Intern
TUKL-NUST R&D Center
Worked on classification of EEG signals into normal and abnormal using convolutional and transformer-based models. Proposed a novel architecture for EEG classification that achieved state-of-the-art performance on the NMT dataset, outperforming previous baselines by 10%.
EEGPyTorchTransformersDeep Learning
Education
Bachelor of Engineering in Software Engineering
National University of Sciences & Technology
Gold Medalist with a CGPA of 3.91. Relevant interests include data structures, algorithms, operating systems, database systems, and machine learning.
CGPA 3.91Gold MedalistSoftware Engineering
Publications
EEGWriter: A Multimodal Deep Learning Framework for Automated EEG Diagnostic Report Generation
Muhammad Athar, Hira Masood, Faisal Shafait and Hassan Aqeel Khan
ICPR · 2026
Assessing Vulnerabilities to Adversarial Perturbations in EEG-Based Pathology Detection Systems
Hira Masood, Maham Jahangir, Muhammad Athar, Muhammad Imran Malik, Faisal Shafait & Hassan Aqeel Khan
ICPR · 2026
Skills
Languages
What I write in- C/C++
- C#
- Python
- SQL
- JavaScript
- TypeScript
- Dart
- Java
Libraries & Frameworks
What I build with- PyTorch
- TensorFlow
- LangChain
- React
- Flutter
- Node.js
- Django
- Flask
- Pandas
- NumPy
Tools & Platforms
Where I work- Git
- Docker
- Google Cloud
- Linux
- Bash
- Neovim
- Tmux
Off the clock
What I do for fun- Mathematics
- Rubik's Cube
- Chess
- Puzzles
- Sketching
- Cats