Develop performance monitoring and measurement infrastructure that provides consistent observability across simulation, emulation, and silicon environments.
Build scalable data pipelines and full-stack dashboards to ingest, visualize, and compare performance metrics across builds and environments.
Coordinate with GPU architects to craft infrastructure for performance verification of upcoming architectures.
Work closely with HW teams to automate and accelerate verification workflows, enabling faster GPU build iteration.
Empower GPU architects by providing insights to understand current performance and model industry-leading performance for future builds.
Improve the daily workflows of the world's top chip architects, contributing to the creation of the next greatest generation of GPUs!
What we need to see
BS/MS in Computer Science, Computer Engineering, or equivalent experience.
3+ years of software engineering experience, primarily in C++, with Python for tooling and automation.
Strong CS fundamentals, including data structures, algorithms, OOP, and system design.
Full-stack experience with backend (Java/Python), REST APIs, and modern frontend (React/Ember) for data-intensive applications is a plus.
Proficiency in databases (SQL, MongoDB) for metrics storage and querying is a plus.
Hands-on experience with Git, CI/CD, Kubernetes, Docker, and messaging systems (RabbitMQ) is a plus.
Exposure to GPU/CPU/SoC chip performance verification is a plus.
Familiarity with AI development tools.
Excellent interpersonal skills.
#LI-Hybrid
