Portfolio · v2026 Lahore, PK

Muhammad
Zeeshan

¹ Lahore University of Management Sciences · Research Assistant
² ICMA Digital Academy · Instructor, Generative AI
Abstract

Machine learning engineer working on generative AI, retrieval-augmented systems, and applied deep learning. First-author at IEEE ICASSP 2026. I build RAG pipelines, multi-agent LLM applications, and computer-vision models — and ship them to GCP and AWS.

§ Publications

Peer-reviewed research.

§ Selected Work

Things I've built.

§ Experience

Where I've worked.

§ Education

Where I studied.

§ Stack

Tools of the trade.

Languages
Python, SQL, Java, C++
ML & Deep Learning
PyTorch, TensorFlow, Scikit-learn, NumPy, Pandas, OpenCV, CNNs, Transformers, Autoencoders, GANs, Transfer Learning
Generative AI & LLMs
Hugging Face, LangChain, OpenAI API, GPT-4o, BERT, T5, XLM-RoBERTa, CLIP, RAG, Supervised Fine-Tuning, Chain-of-Thought, Instruction Tuning, Multi-Agent LLMs, Prompt Engineering
Retrieval & Vector DBs
Weaviate, ChromaDB, Embeddings, Semantic Search, Reciprocal Rank Fusion
Cloud — GCP (primary)
Cloud Run, Cloud Build, Artifact Registry, Cloud SQL, Compute Engine, Cloud Storage, Vertex AI, Cloud Functions
Cloud — AWS
EC2, S3, Lambda, Bedrock, ECR, Fargate, Elastic Beanstalk, CloudFront
DevOps & CI/CD
Docker, GitHub Actions, Google Cloud Build, Terraform, FastAPI, Streamlit, Git
§ Contact

Let's talk.

I'm open to roles in ML engineering and applied research, particularly around LLMs, retrieval, and applied deep learning. The fastest way to reach me is email — I usually reply within a day.