Skip to content
View sohams25's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report sohams25

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
sohams25/README.md

Hello there! 👋

I am Soham, an Electronics and Communication Engineering graduate from BITS Pilani, Goa. I build at the intersection of Computer Vision and Edge AI deployment.

Currently, I am a Machine Learning Engineer at Clutterbot Technologies, focusing on perception pipelines for indoor robotics. My research journey includes working on Affective Computing in Education at NTU, Singapore, Artwork Scene Understanding at TCS Research, and Cultural Heritage Preservation through deep learning at CSIR-CEERI, Pilani.

I am particularly passionate about hardware-specific optimization for NVIDIA Jetson and Qualcomm platforms. Whether it was leading the autonomous subsystem for Project Kratos or engineering smart-glasses in Project Visio, I thrive on making models run efficiently in resource-constrained environments.

Outside of work, you will usually find me brewing Blue Tokai in a French press, bouldering, or planning for treks in the Himalayas.

If you are looking to collaborate on any AI, CV, or robotics-based projects, feel free to reach out! =)

Email: [email protected]


Building for the edge, one optimization at a time.

Pinned Loading

  1. prism-ros prism-ros Public

    Hardware-agnostic ROS 2 perception acceleration. Auto-detects host accelerators (Intel VA-API/NVIDIA NVMM) at runtime to dynamically construct zero-copy GStreamer pipelines directly from standard R…

    C++ 3

  2. sohams25.github.io sohams25.github.io Public

    Forked from jonbarron/jonbarron.github.io

    HTML