Soumik Rakshit is a Machine Learning Engineer working on end-to-end deep learning pipelines as part of the Growth team at Weights & Biases, the platform used by ML teams to track experiments and production models. His research and development interests include generative machine learning models, video enhancement systems, neural radiance fields, and NLP-based solutions that improve and automate student evaluation in the education sector.

A defining habit of Soumik’s work is making research usable. He enjoys implementing papers from machine learning and computer graphics, then communicating the ideas through end-to-end notebooks and articles so that other practitioners can reproduce and build on them rather than starting from a PDF and a blank editor.

He also works at the frontier of training infrastructure, training machine learning models on TPUs using JAX, Flax, TensorFlow, and Keras. That mix of research implementation, open communication, and hardware-aware deep learning engineering defines his approach to modern ML.