Skip to content
View pranshuk22's full-sized avatar

Highlights

  • Pro

Block or report pranshuk22

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.

Content in all repositories owned by your account will be closed.
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
pranshuk22/README.md
Pranshu Kumar: software engineering, systems programming, machine learning and robotics

Portfolio Resume LinkedIn Email
Explore my website

Final-year undergraduate at IIT Kanpur, majoring in Electrical Engineering and Chemical Engineering with minors in Machine Learning, Computer Systems and Management Sciences.

My interests span full-stack engineering, systems programming, machine learning and robotics, with a growing interest in reinforcement learning. I recently interned as a Software Engineer at Samsara (May to Jul 2026). I enjoy turning complex technical problems into reliable, well-tested software.

Contribution graph snake

Tech Stack

Tech stack: Languages (Python, C++/C, Go, TypeScript, JavaScript, SQL, Bash, GLSL, LaTeX); Backend and Databases (Next.js, NestJS, PostgreSQL, Prisma, REST APIs, WebSocket, JWT); Machine Learning and Robotics (PyTorch, scikit-learn, OpenCV, ROS / ROS2, Gazebo); Scientific Computing (NumPy, Pandas, Matplotlib, MATLAB, Numba); Systems and DevOps (gRPC, Docker, Kubernetes, Linux, MPI); Developer Tools (Git, GitHub, Postman)

Projects

Computer Graphics: WebGL2 Rendering Engine Parallel Computing: 3D Stencil in MPI Model-Based and Policy-Gradient RL DeepCDA Reproduction More projects on my portfolio

Contact Me

Portfolio LinkedIn Email Resume

Pinned Loading

  1. MeChess MeChess Public

    A chess engine that plays like you: your openings, your style, at a rating you choose. C++ engine + Python toolkit trained on your own games.

    Python 3

  2. DeepCDA DeepCDA Public

    Deep Learning & Domain Adaptation: reproduction and evaluation of DeepCDA for compound-protein affinity prediction (encoder, ADDA, SimBoost/DeepDTA benchmarks)

    Python

  3. CS360 CS360 Public

    Coursework for CS360: Introduction to Computer Graphics (IIT Kanpur). WebGL assignments on 2D rendering, shading, texture and environment mapping, shadow mapping, and ray tracing.

    JavaScript

  4. CS633-Assignments CS633-Assignments Public

    CS633 Parallel Computing assignments in C/MPI, run on the PARAM Rudra cluster with SLURM: (1) blocking point-to-point exchange at rank distances D1/D2, (2) 3D stencil with non-blocking halo exchang…

    C

  5. CS771-Project-2 CS771-Project-2 Public

    Prototype-based continual learning on CIFAR-10: incrementally trained Learning-with-Prototypes classifiers over a stream of datasets (with a distribution-shift phase), using cached ResNet-50 features.

    Jupyter Notebook

  6. EE675-Project EE675-Project Public

    Reinforcement learning coursework: a predator-prey MDP solved with dynamic programming and model-based kernel estimation, and a REINFORCE policy-gradient agent trained with SGA and Adam.

    Python