Ashwin Ramesh
Machine Learning Engineer at Adobe
San Jose, California, United States
Summary
🤩
Rockstar🎓
Top SchoolAshwin Ramesh is a Machine Learning Engineer with a decade of experience building production-ready computer vision and generative AI systems, currently contributing to Adobe Firefly in San Jose. He combines strong academic credentials—a 4.0 MS in Computer Science from the University of Rochester and a BTech from NIT Karnataka—with hands-on expertise in neural networks, deployment on edge devices, and scalable CI/CD for inference servers. His work spans real-time video analytics, object detection and tracking on NVIDIA Jetson/Xavier, and speech/NLP pipelines, plus practical cloud integrations for Triton Inference Server (S3/GCS CI enhancements). Known for turning research into robust production modules, he also brings a mechanical-engineering mindset to solve geometry and search problems, such as a 3D image search engine for CAD workflows.
10 years of coding experience
4 years of employment as a software developer
CBSE - 12th Grade, PCMC, 97.2%, CBSE - 12th Grade, PCMC, 97.2% at CMR National Public SchoolICSE - 10th Grade, 94.2%, ICSE - 10th Grade, 94.2% at New Horizon Public SchoolMaster of Science - MS, Computer Science, 4.0, Master of Science - MS, Computer Science, 4.0 at University of RochesterBachelor of Technology, Mechanical Engineering, Bachelor of Technology, Mechanical Engineering at National Institute of Technology Karnataka
English, Tamil, Hindi
Github Skills (18)
cloud-computing10
inference10
cicd10
gcp10
amazon-s310
cloud-storage10
aws-s310
devops10
s3-bucket10
testing9
dockers9
docker9
aws9
kubernetes-pods8
gpu8
Programming languages (2)
Github contributions (5)
triton-inference-server/server
Jun 2019 - Aug 2019
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Role in this project:
DevOps Engineer & Cloud Engineer
DevOps Engineer & Cloud EngineerContributions:11 reviews, 10 commits, 29 PRs in 1 month
Contributions summary:Ashwin's contributions primarily revolve around enhancing the Continuous Integration and Continuous Deployment (CI/CD) pipeline and integrating cloud storage functionalities within the Triton Inference Server project. This includes creating CI jobs to test cloud storage implementations, specifically for Google Cloud Storage (GCS) and S3. The user addressed build issues, implemented cloud storage features, and modified the testing framework to accommodate cloud storage integration. The modifications include adding support for S3, fixing bugs related to GCS, and updating the CI test to include bucket testing.
nvidia-dockernvidiadeep-learninggpuinference
xprotobeast2/shwinOS
Feb 2016 - Dec 2017
Contributions:1 push, 2 branches in 1 year 10 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.