Abhilash Shankarampeta
Jr Applied Scientist at Amazon
San Diego, California, United States
Summary
👤
Senior🎓
Top SchoolAbhilash Shankarampeta is a machine learning engineer with a decade of experience building production ML systems, currently at Cisco after roles at Amazon and Meesho and an MS in Data Science from UCSD. He has driven large-scale search and ranking improvements for 130M+ monthly users, shipping low-latency multimodal retrieval, query understanding, and MoE-based ranking that materially boosted long-tail and new-product conversion. His background spans industry and research—publishing on Tabular NLI and contributing fixes to the high-profile pytorch/vision repo—reflecting both applied deployment expertise and attention to model robustness. Comfortable with GPU inference stacks (Nvidia Triton) and multilingual/deep representation models (XLM-R, FLAVA), he combines systems thinking with hands-on model optimization. Notably, he blends product impact and community building, having organized NLP communities at IITG and contributed open-source fixes to core vision tooling.
10 years of coding experience
2 years of employment as a software developer
University of California, San DiegoBachelor of Technology Electronics and Communications Engineering, Bachelor of Technology Electronics and Communications Engineering at Indian Institute of Technology, Guwahati
Telugu, English, Hindi
Stackoverflow
577reputation
57kreached
29answers
4questions
Github Skills (21)
pytorch10
python10
model-driven10
machine-learning10
model-building10
deep-learning10
computer-vision10
modeling10
model-driven-development10
data-science9
image-processing8
git7
scipy7
cs506
data-structures6
Programming languages (8)
Github contributions (5)
pytorch/vision
Mar 2020 - May 2020
Datasets, Transforms and Models specific to Computer Vision
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 4 commits, 5 PRs in 2 months
Contributions summary:Abhilash contributed to the `pytorch/vision` repository by addressing several issues within the codebase related to computer vision models and datasets. Their work included adding warnings and notes for dependencies like `scipy`, removing Python 2.x code, and replacing `imp` with `importlib`. They also implemented a check for degenerate bounding boxes in the generalized RCNN model and fixed atrous rates for the `deeplabv3_mobilenet_v3_large` model.
pytorchvisiondeep-learningdatasetcomputer-vision
nvs-abhilash/HackerEarth
Jan 2016 - Oct 2016
Contributions:56 commits, 48 pushes, 2 branches in 8 months
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.