Olivia Jain
Software Engineer at Acorns
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolOlivia Jain is a software engineer with nine years of hands-on experience and a strong focus on ML infrastructure, having shipped performance improvements at Microsoft’s ONNX Runtime and built ML platform features at Abacus.AI. Based in San Francisco, she currently engineers at Acorns and brings deep backend expertise across CUDA, TensorRT, OpenVINO, Docker, and cloud deployment pipelines. She led performance testing and regression monitoring for hundreds of models at Microsoft, improving latency and memory tracking and coordinating large cross-team releases with wide downstream distribution. A UC Berkeley CS graduate who continued study at Stanford Engineering, Olivia seeks roles offering ownership, mentorship, and fast technical growth. She pairs a curiosity for hard systems challenges with a commitment to building inclusive communities and enjoys tackling the less obvious bottlenecks that unlock production ML performance.
9 years of coding experience
5 years of employment as a software developer
Bachelor of Arts - BA, Computer Science, Bachelor of Arts - BA, Computer Science at University of California, BerkeleyEnergy Innovation and Emerging Technologies Certification, Environmental/Environmental Health Engineering, Energy Innovation and Emerging Technologies Certification, Environmental/Environmental Health Engineering at Stanford University School of EngineeringHigh School Diploma, High School Diploma at Los Altos High School
English
Github Skills (12)
tensorrt10
onnx10
python10
hardware-acceleration10
performance-testing10
cuda8
cua8
compiler7
build-process6
build-tools6
build-system6
machine-learning5
Programming languages (3)
Github contributions (5)
microsoft/onnxruntime
Sep 2020 - Apr 2022
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Role in this project:
Performance Engineer
Performance EngineerContributions:2 releases, 105 reviews, 361 commits in 1 year 7 months
Contributions summary:Olivia's contributions primarily focus on improving the performance testing infrastructure for the ONNX Runtime. They refactored the performance testing scripts, including changes to latency reporting and data collection. They added features such as tracking and reporting of memory usage during TensorRT execution. The user also made several changes to the build and execution processes within the testing framework, which indicates an effort to improve the efficiency of performance analysis.
machine-learningonnxruntimedeep-learningonnxneural-networks
mwakaba2/onnxruntime
Feb 2021 - May 2021
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Contributions:165 commits in 2 months
machine-learningonnxruntime
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.