GPGPU Performance Tooling Engineer

rivos

| Santa Clara, California, United States (Hybrid) | Full Time | 7 months ago

Apply Now

Job Summary

We are seeking a talented individual to work on software aimed at enhancing the Deep Learning ecosystem and assisting hardware engineers in building advanced Deep Learning parallel systems. The role focuses on designing and implementing features for the Perfetto framework, enabling users to more efficiently measure code performance. This position may involve working on the lower-level libraries that support performance data collection. The candidate will gain technical and organizational skills from experienced professionals, learning to write performant and readable code, manage projects effectively, and collaborate with the Open Source community. We are strong advocates for Open Source and Free software, contributing our improvements back to the projects we utilize.

Must Have

Experience with Perfetto profiling framework
Ability to write code in C or C++
Experience with Protobuf
Understanding of computer architecture
Strong problem-solving skills
Excellent communication skills

Good to Have

Experience profiling GPGPU architectures
Familiarity with deep learning frameworks
Ability to write code in Rust
Coursework/experience with Machine Learning

Job Description

We are working on software to improve the Deep Learning ecosystem and help hardware engineers build great Deep Learning parallel systems.

We are looking for a strong candidate with a background in writing systems software and working with GPGPU performance tools and tracing frameworks such as Perfetto.This role involves designing and implementing features for the Perfetto framework to enable Rivos internal and external users to more easily measure the performance of their code. This role may also go much lower into the libraries that enable performance data collection.

You will be learning technical and organizational skills from industry veterans: how to write performant and readable code; how to structure and communicate projects, ideas, and progress; how to work effectively with the Open Source community.

We are big proponents of Open Source and Free software and contribute back our improvements to all the great projects we use.

Responsibilities

Develop and modify the Open Source Perfetto framework to enable software developers to improve performance of their code.
Work on underlying libraries and drivers to enable performance data collection.
Ensure performance monitoring overhead is minimized
Build tooling to facilitate measuring performance in different scenarios (on simulators, FPGAs, or real hardware)
Write unit tests and benchmark tools to validate the performance and correctness of your changes.
Stay current with advancements in the field.

Requirements

Experience with Perfetto profiling framework
Ability to write code in C or C++
Experience with Protobuf
Understanding of computer architecture
Strong problem-solving skills and ability to work in a fast-paced, collaborative environment.
Excellent skills in problem solving, written and verbal communication
Strong organization skills, and highly self-motivated.
Ability to work well in a team and be productive under aggressive schedules.

Optional Requirements

Experience with profiling and optimizing low-level performance (memory bandwidth, latency, throughput) on GPGPU architectures.
Familiarity with deep learning frameworks (TensorFlow, PyTorch, etc.).
Ability to write code in Rust
Coursework or experience with Machine Learning algorithms