Open to AI / ML internships & roles

Afzal Hussain —
I build things that learn.

Final-year Data Science & AI undergraduate at IIT Guwahati. I work on machine learning systems end to end — from messy data to trained models to something you can actually click on. Off the keyboard, I teach, and I make short films about studying well.

See the work Get in touch GitHub

Built & shipped

Projects

Four systems I've built from scratch — retrieval, tabular ML, speech and vision.

Finance RAG Pipeline

LangChain · ChromaDB · Python

A retrieval-augmented question answering pipeline over financial documents: chunking, embedding-based retrieval from a vector store, and an LLM answer stage. Built as the first piece of a larger multi-agent orchestration system.

View repository →

Health Data Classification — NHANES

XGBoost · LightGBM · CatBoost · Optuna · SHAP

A binary classification pipeline on NHANES health survey data, built during the Summer Analytics 2026 Hackathon (IITG Consulting & Analytics Club). Class imbalance handled with SMOTE, tuning with Optuna, three boosters combined in a soft-voting ensemble, and SHAP used to explain what the model actually keys on. Now being extended into a comparative research paper on explainable ML.

Voice Intent Classifier

Whisper · BERT · PyTorch

Speech in, intent out. Whisper transcribes the audio, a fine-tuned BERT classifier maps the transcript onto intent labels — the front half of any voice-driven assistant.

CNN Image Classifier

PyTorch · CIFAR-10 · Flask

A convolutional network trained on CIFAR-10 on a Colab T4 GPU, then wrapped in a Flask interface so predictions run in a browser rather than a notebook.

Sketchbook

Ideas in the pipeline

Things I'm poking at — some will become real, some won't.

Low-cost AI glasses Siliguri Connect Creator collaboration app Offline screenshot & photo organiser Personal AI day planner

Off the keyboard

Teaching & content

Study with Afzal

  • Short-form educational video on Instagram and YouTube Shorts.
  • AI tools, study strategy, and how to actually get through a syllabus.
  • Written, shot and edited solo — the whole production pipeline is mine.

Private tutoring

  • Three years teaching Science, Maths, Social Science and English, in person and online.
  • Physics, Chemistry and Biology through the senior school grades.
  • An independent practice: outreach, scheduling, lesson design and tracking progress.

Toolkit

What I work with

LanguagesPython · JavaScript · SQL
ML & DataPyTorch · scikit-learn · XGBoost · LightGBM · CatBoost · Optuna · SMOTE · SHAP · pandas · NumPy
AI SystemsLangChain · LangGraph · ChromaDB · RAG · BERT · Whisper · OpenCV · Ollama
EngineeringFlask · React · SQLite · REST APIs · Playwright · Git · Google Colab

Background

Education

B.Sc. Data Science & Artificial Intelligence

IIT Guwahati · Mehta Family School of DS&AI · 2023 – 2027

Nepal AI School 2025

Participant

Research in progress

Comparative study of gradient-boosting models with SHAP explainability on health survey data

Say hello

Contact

Internships, collaborations, tutoring enquiries — all welcome.

This opens your own mail app with the message ready to send.