Machine Learning Engineer & GenAI Specialist
Hi, I'm Bismillah Jan.
My work bridges applied ML research and production engineering; taking ideas from the lab through to GenAI systems in the real world.
Machine learning engineer and researcher with experience across medical image analysis, production ML systems, technical curriculum development, and scalable software architecture. I work primarily in deep learning and computer vision, extending into NLP and retrieval-augmented systems, with a focus on healthcare.
More about meSelected work
Featured projects
A few things I've built across RAG, fine-tuning, and agentic systems.
RAG + SQL Query Engine
An AI-powered question-answering system built with LlamaIndex that retrieves answers from both unstructured documents and structured SQL databases in a single query.
Multi-Agent Content Creation with CrewAI
A collaborative content pipeline built in Python and CrewAI, using role-specific agents for outlining, writing, and validation.
Localized RAG System with ChromaDB
A topic-aware retrieval-augmented generation solution using agents and ChromaDB to deliver concise, user-specific answers.
Writing
Latest from the blog
Notes on RAG, fine-tuning, agents, and shipping GenAI to production.
Sampling Your Way to Generation: Inside the VAE
A VAE's encoder outputs a distribution, not a single code, and that one change is what lets it generate, not just reconstruct. Here's how reconstruction and KL shape the latent space, why the reparameterization trick keeps training differentiable, and how to read blur, posterior collapse, and bad samples as symptoms with fixes.
Building a Retrieval-Augmented Generation Pipeline From Scratch
A walkthrough of the moving parts behind a production RAG system — chunking, embeddings, retrieval, and grounding an LLM's answers in real sources.
Fine-Tuning LLMs: LoRA vs Full Fine-Tuning
When parameter-efficient fine-tuning gets you 95% of the way there, and when you actually need to update every weight.
Have a project in mind?
I'm always open to talking about ML/GenAI work, collaborations, or interesting problems.
Say hello