Janet Yang
Software Engineer at Meta
Greater Seattle Area United States
Summary
🤩
Rockstar🎓
Top SchoolJanet Yang is a software engineer with 7 years of experience specializing in ML inference and compiler optimizations for AI acceleration, currently working at Meta on PyTorch GPU inference enablement for recommendation models. She has contributed to high-impact open-source projects like the Glow compiler, implementing native NNPI ops and performance optimizations that bridge compiler backends and hardware kernels. Her background spans AI infrastructure internships and research at Carnegie Mellon, where she built adaptive tutoring and interactive NLP-driven apps, demonstrating a blend of applied research and production engineering. Janet's experience spans low-level performance work (TensorRT, AITemplate, TorchInductor) and full-stack development from earlier roles, giving her a rare cross-cutting view of model-to-hardware deployment. Pragmatic and detail-oriented, she often focuses on subtle operator reorderings and kernel gating that yield outsized performance gains in real workloads.
7 years of coding experience
2 years of employment as a software developer
High School, High School at State College Area High SchoolBachelor's degree Computer Science, Bachelor's degree Computer Science at Carnegie Mellon University
Chinese, English
Github Skills (12)
machine-learning10
caffe10
c-language10
cprogramming-language10
tensorflow9
operation9
back-end-development9
tensorrt9
tensor9
compiler-design8
performance-optimization8
python7
Programming languages (2)
Github contributions (5)
pytorch/glow
Mar 2021 - Jun 2022
Compiler for Neural Network hardware accelerators
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:2 reviews, 43 commits, 39 PRs in 1 year 2 months
Contributions summary:Janet primarily contributed to the development and optimization of the Glow compiler for neural network hardware accelerators. Their work included implementing the SoftPlus operator using a native NNPI op within the Caffe2 loader and improving the performance by swapping Tile and Clip operators. Furthermore, the user created flags for gating custom IA and DSP kernels and made various changes to support operations like Scale, GaussianFill, and BatchSparseToDense. They also added support for the implementation of BatchSparseToDense and FillExamplesWithIndicator and addressed a number of tests.
hardware-acceleratorscompilerneural-networkacceleratorshardware
qxy11/pytorch
Apr 2021 - Aug 2024
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Contributions:18 pushes, 14 branches in 3 years 4 months
pythongpu-accelerationdeep-learninggpuacceleration
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.