Geoffrey Martin-noble
Principal Member Of Technical Staff at AMD
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolGeoffrey Martin-noble is a Principal Member of Technical Staff with 11+ years building robust infrastructure, compilers, and ML systems, currently enabling biotech ML models on AMD GPUs from Seattle. He’s a hands-on engineer who moves from root-cause analysis to production-ready solutions, repeatedly reducing friction for other users across build systems, runtimes, and compiler stacks. At Google he was a top contributor to IREE and MLIR, led cross-repo builds and benchmarks, and helped shepherd tooling used across diverse hardware targets. His open-source work includes integrating TensorFlow Federated with the IREE backend and improving TensorFlow runtime build automation, reflecting deep expertise in C++, Bazel/Starlark, and ML compiler toolchains. Geoffrey prefers mission-driven roles that have tangible societal impact—currently focused on accelerating drug discovery—and is selective about opportunities that match that criterion.
11 years of coding experience
11 years of employment as a software developer
Bachelor’s Degree Computer Science and Chemistry, Bachelor’s Degree Computer Science and Chemistry at Haverford CollegeLakeside School, Seattle
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (19)
unit-testing10
c-language10
python10
cmake10
mlr10
tensorflow10
bazel10
build-automation10
irr10
cprogramming-language10
test-automation10
codegen9
refactor9
machine-learning9
build-system9
Programming languages (22)
Github contributions (5)
iree-org/iree
Sep 2019 - Jan 2023
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Role in this project:
Backend Developer & Test Automation Engineer
Backend Developer & Test Automation EngineerContributions:2385 reviews, 1153 commits, 2123 PRs in 3 years 4 months
Contributions summary:Geoffrey's contributions to the `iree-org/iree` repository primarily involve changes related to IREE's core code. They focused on enhancing the project's testing framework by incorporating new tests, improving the quality of existing tests. The user was involved in integrating the LLVM toolchain to improve build processes, refactoring code and updating the build files. Their contributions include significant focus on implementing and ensuring the robustness of the unit tests.
mlirspirvvulkantensorflowcompiler
google-parfait/tensorflow-federated
Jun 2021 - Sep 2022
An open-source framework for machine learning and other computations on decentralized data.
Role in this project:ML Engineer
ML EngineerContributions:7 commits in 1 year 2 months
Contributions summary:Geoffrey contributed to the TensorFlow Federated (TFF) project by making several updates related to integrating with the IREE (MLIR-based) backend. Their work involved deleting assertions, explicitly specifying input types for compilation, updating driver names, adapting to API changes for module creation, and removing a prototype IREE backend. These changes indicate a focus on supporting and refining the integration of TFF with IREE for model execution.
pytorchdeep-learningmachine-learningsecure-computationfederated-learning
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.