Shreyas Somashekar
Staff SDE - AI Engineering at Gruve
Bengaluru, Karnataka, India
Summary
👤
Senior🎓
Top SchoolShreyas Somashekar is a Staff SDE in AI Engineering with 10 years of experience building production-grade computer vision and ML systems that deliver measurable business impact. He has architected MLOps pipelines that cut API usage by 90%, improved CV model performance 6x, and expanded detected classes fourfold, demonstrating a blend of systems thinking and model-level optimization. His projects span LangChain-powered QA generation and multimodal exam integrity POCs that fuse audio and video streams—practical solutions that reduced manual work and strengthened trust in automated assessments. Early work includes deploying mobile-friendly detection and super-resolution techniques and generating millions of synthetic images to harden OCR pipelines, showing a strong grounding in dataset engineering. A hands-on mentor and cross-functional collaborator, he pairs deep technical skills (MLOps, CV, NLP, LLMs, FastAPI) with a pragmatic focus on scalability and operational reliability. Based in Bengaluru with an electrical engineering master’s background, he’s equally comfortable prototyping research ideas and shipping robust cloud-native systems.
10 years of coding experience
5 years of employment as a software developer
Bachelor of Engineering (B.E.), Electrical, Electronics and Communications Engineering, First Class, Bachelor of Engineering (B.E.), Electrical, Electronics and Communications Engineering, First Class at Visvesvaraya Technological UniversityMaster's degree, Electrical and Electronics Engineering, Master's degree, Electrical and Electronics Engineering at University of Central Florida
Github Skills (32)
calculator10
video-processing10
filename10
audio-processing10
binary-classification10
sliding-window10
testing9
mediapipe9
pipeline-framework9
machine-learning9
inference9
graph-framework9
perception9
tensorflow9
theano9
Programming languages (4)
Github contributions (5)
shreyas0906/Selfies-with-sunglasses
May 2016 - Apr 2021
Contributions:92 commits, 77 pushes, 2 branches in 4 years 11 months
shreyas0906/Object-detection-with-deep-learning-and-sliding-window
Sep 2016 - Aug 2019
Introduces an approach for object detection in an image with sliding window. The repository contains three files, make_data.py reads the image in gray scale and converts the image into a numpy array. The labels are also appended based on the file name. In this case, if the file name starts with "trn", then 1 is appended else 0. Finally, all the images and labels are saved into .npy file. The test-model-1.py file loads the images and converts the labels into two categories as we are doing binary classification of images. The model is built using keras with theano as backend. In this case, the best training accuracy was 80% since the data was just 500 images and the testing accuracy was 67%
Contributions:15 commits, 10 pushes, 2 branches in 2 years 10 months
backendbinary-classificationfilenamegrayscalekeras
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.