Skip to content
View Bhavikupadhyay's full-sized avatar
2 followers · 0 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLO

Block or report Bhavikupadhyay

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Bhavikupadhyay/README.md

I am an Applied AI Engineer who builds across the stack, from autonomous AI agents to GPU kernels. I can design and architect new systems from scratch, but I am just as comfortable jumping into an existing codebase to optimize and maintain it.

I thrive in environments that demand velocity and rapid adaptation. Give me an ambiguous problem, and I will ship the solution.

USC MS CS '25

Available immediately.

bhavikupadhyay08@gmail.com

Portfolio · LinkedIn

Stack

Languages

Python C++ C C# TypeScript JavaScript CUDA

ML & AI

PyTorch Triton TensorFlow HuggingFace LangChain OpenCV Scikit-Learn Weights & Biases ONNX

Systems & Infra

Docker Kubernetes AWS GCP CMake GitHub Actions PostgreSQL MongoDB Redis

Web

React Next.js Angular FastAPI Node.js Django

Stats

Pinned Loading

  1. otter otter Public

    A from-scratch autodiff library in C++17 — tensor runtime, memory management, and computational graph with multi-backend support

    C++ 1

  2. coverage-agent coverage-agent Public

    Autonomous multi-agent pipeline that analyzes branch coverage gaps, generates targeted tests, and validates them in an E2B sandbox to improve code coverage.

    Python 1

  3. triton-kernels triton-kernels Public

    22 progressive Triton GPU kernels, from elementwise ops to Flash Attention v2, featuring correctness tests and PyTorch throughput/TFLOPS benchmarks.

    Jupyter Notebook 1

  4. CS402-Weenix-Kernel CS402-Weenix-Kernel Public

    Unix-like OS kernel implementation featuring Threads, VFS and Virtual Memory Components developed for USC CS402

  5. cifar-image-generator cifar-image-generator Public

    A modern, modular PyTorch implementation of a Denoising Diffusion Probabilistic Model (DDPM) optimized for generating high-quality CIFAR-10 images. Features a production-ready training pipeline inc…

    Python 1

  6. SnakeAgent SnakeAgent Public

    Train and evaluate deep reinforcement learning agents (DQN, PPO, A2C) to play the classic Snake game using Stable-Baselines3 and PyTorch.

    Python