What can a machine learn? I like finding out.
Hi, I'm Arjun, a software engineer who enjoys building and testing machine learning systems. When I'm not coding, you'll find me exploring the outdoors and photographing birds.
- Currently
- AI Applications Engineer Intern @ Micron Technology
- Based in
- Ahmedabad, India
- Find me
- GitHub/ArjunBasandrai · LinkedIn/arjun-basandrai
Things I've built
01 Machine Learning · ResearchAdaptive Resampling based Training for Imbalanced Classification A modality-agnostic adaptive resampling method to handle class imbalance in supervised classification. Paper submitted to MLWA Journal. 02 ML SystemsElixir Chess Engine A 3500 ELO rated chess engine built from scratch in C++, with a hand-crafted evaluation, a custom-trained NNUE neural network, and a NegaMax search. 03 Computer Vision · Full StackBirdly Bird Identifier A large-scale bird classifier trained on 1M+ images of 1250 Indian bird species, using Google Cloud TPUs and a custom dataset.
What I work on
01
Machine Learning
A model is only as good as the data and the evaluation behind it, and that is where most of my work goes.
PyTorchNumpyscikit-learn
02
MLOps
I take models out of the notebook: packaging them, serving them, and tracking experiments and metrics in production.
DockerMLflowDVC
03
Full-Stack Engineering
I build the API and the interface around a model so it becomes something people can actually use.
TypeScriptReactFastAPI
The other half of the story.
When I'm not building models, I'm usually out photographing birds. And this is where a lot of the patience and attention to detail I bring to my work comes from. I write about my birding adventures on a separate blog.