About
I work at the intersection of research and production — training models, building ML systems, and closing the gap between experiment and deployment. My focus is applied computer vision: getting research ideas to actually ship in production environments.
This blog is where I write down what I learn — practical guides on model architectures, training at scale, deployment pipelines, and the engineering decisions that make research usable. I try to write the articles I wish had existed when I was figuring something out.
Stack
Frameworks
Languages
Infrastructure
Specialties
What I write about
Model Architectures
ViT, Mamba, KAN, DenseNet, YOLO and more — from the paper to the implementation.
Training at Scale
Distributed training, AMP, quantization, CUDA kernels, and profiling for speed.
MLOps & Deployment
MLflow, Kubeflow, LitServe, ONNX, edge devices — taking models to production.
Foundational Models
CLIP, BLIP-2, VLMs, stable diffusion, DINO — how the big models actually work.
Python for ML
Functional tools, concurrency, Rust extensions — the language features that matter.
Ready to dive in?
Browse 100+ articles or pick a series path and go start to finish.