Hey, I'm Parth
I'm a Senior AI Engineer at Kadoa, building an AI-native data platform that runs itself: web-scale extraction, anti-bot infrastructure, and agentic operations that keep humans out of the loop.
I enjoy writing technical articles, solving problems, and collaborating with curious minds. Outside work, you'll likely find me with a book or exploring nature.
Latest Articles
Projects
Master thesis: trained UNet-family and RETFound models under differential privacy and benchmarked mechanisms that recover the accuracy lost to privacy noise.
Implemented custom Kubernetes scheduling policies and measured workload interference across co-located latency-critical and batch jobs.
Adapted state-of-the-art 3D instance segmentation to architectural scenes, scaling the class vocabulary 13.8x on ScanNet++.
Compared Opacus and fast differential privacy for training on medical images, measuring the speed, memory, and privacy trade-offs.
Transformed data into insights with classifier evaluation, Lucene indexing, NLP, embeddings, RAG, and decision tree visualizations.
Compared gradient clipping techniques in DP-SGD and measured their impact on model accuracy.
Implemented algorithms with perceptron, classification, regression, boundary detection, image restoration, and deep neural network feature design.
Prediction of loan approval based on applicant details using logistic regression model.
A free, open url scraper for Ali Express integrated with Google Spreadsheet helping drop-shipping business.
A Python package which makes very simple to run things in the background of a python application, be it a CLI app, or a web app