AI Engineer · Machine Learning Engineer
I build deployed ML systems: production pipelines for healthcare AI, LLM applications, and large-scale signal decoding, with measurable real-world impact.
I'm an AI and Machine Learning Engineer focused on shipping production ML systems. End-to-end pipelines that move from raw data to deployed inference, with measurable impact on accuracy, latency, and cost.
I've built and deployed pipelines used by clinicians and researchers, from EEG-based emotion and seizure models across 500+ subjects to U-Net segmentation on 10k+ medical images, plus a suite of LLM applications spanning RAG, vision-language OCR, and fine-tuned clinical assistants.
My work is grounded in research credibility: two peer-reviewed papers accepted at eNeuro and Brain-Apparatus Communication on applied deep learning for brain-signal analysis, bringing rigor to the engineering rather than the other way around.
22 projects spanning neural decoding, medical imaging, and LLM applications, each shipped with measurable impact.
Scalable ML platform with automated parameter prediction for EEG model benchmarking and intelligent ingestion workflows.
Retrieval-Augmented Generation system for chest X-ray interpretation using CLIP cross-modal retrieval and Groq LLM.
Neuro-inspired graph-based temporal-spatial model combining GAT and LSTM for EEG cognitive state prediction.
GNN-based optimization system for seizure detection on the TUH EEG dataset with hyperparameter optimization.
Graph neural network–based predictive maintenance system for industrial crane systems using sensor data and digital twins.
Streamlit web app enabling OCR and document understanding from uploaded images via vision-enabled Groq LLM.
AI-powered document Q&A system using LLMs and FAISS to answer questions from uploaded PDFs.
Spiking Neural Networks on the ISRUC-Sleep dataset, optimized for low-power edge computing.
Voice/chat assistant using LLMs and multi-criteria decision algorithms for academic recommendations.
U-Net model for segmenting dental CT scans, including nerves, roots, and enamel structures.
AI web app to explore Lahore's history using LLMs and FAISS semantic search over Wikipedia and PDFs.
Attention-based decoder combining temporal, spectral and spatial features across 500+ subjects.
Full-stack secure app for audio diarization, transcription, feature extraction and chatbot querying.
Fine-tuned Meditron LLM with LoRA/QLoRA to replicate USMLE-style clinical reasoning.
Data analysis dashboard for Olympic history with insights into medals, countries, athletes, and trends.
Full-stack AI legal assistant for case research, document summarization and case law referencing.
EEG emotion recognition pipeline with preprocessing, artifact removal and frequency-band features.
Streamlit + MySQL system for managing educational rubrics, CLOs, assessments, and student performance.
DCGAN to generate synthetic MRI scans for brain tumor analysis and data augmentation.
AI chatbot for industrial crane operators, providing answers from operation manuals and troubleshooting guides.
From EEG decoding and medical imaging to predictive maintenance and production-grade LLM systems — building research-grade models that ship.
KICS-UET Lahore
Recognized for AI/ML pipelines, signal processing, and innovative computational methods.
Government of Punjab
Awarded for placing in the top 1% CGPA in Computer Engineering at UET Lahore.
Traversaal.ai
Team TROJAN_AI ranked top 6 of 200+ global teams.
Harvard & MIT (Cambridge)
Recognized for problem-solving and analytical thinking.
Published research in applied AI and deep learning, focusing on real-world problems such as EEG-based brain signal analysis.
Noor Fatima, Ghulam Nabi
A multi-branch deep learning architecture solving two real-world problems at once: secure biometric ID and cognitive-state inference, both directly from raw EEG signals.
Noor Fatima, Ghulam Nabi
Transformer-based pipeline for early Alzheimer's and MCI screening from multimodal EEG, applying modern sequence models to a high-impact healthcare problem.
These publications back the engineering work with strong AI/ML fundamentals and depth in complex, real-world domains like healthcare and neuroscience. The same rigor I bring to shipping production ML systems.
Six focus areas spanning 36+ technologies — refined through peer-reviewed research, production deployments, and applied healthcare AI work.
Modeling, training pipelines, and applied research.
Primary research & production framework
Churn, regression, feature selection
Sequence, graph, and biologically-inspired models.
ResNet–Transformer hybrids, ERP models
NeuroGraph-TSC for EEG
Medical imaging on SageMaker
TriNet-MTL biometrics
Retrieval, fine-tuning, and agentic workflows.
EEG, audio, and biomedical data pipelines.
PSD, DE, ERP, source decoding
STT, TTS pipelines
Shipping research-grade models into production.
Day-to-day engineering toolkit.
Open to AI and Machine Learning Engineer roles, freelance ML projects, and applied research collaborations.
