Senior Engineer, Performance Infrastructure (RISC-V)
TenstorrentJob Title
Senior Engineer, Performance Infrastructure (RISC-V)
Role Summary
Build and operate the performance infrastructure used by the RISC-V Software and RISC-V Performance teams: benchmarking automation, data collection, workload capture and replay across silicon, FPGA/emulation platforms, and performance models.
Enable performance and software engineers to run reproducible experiments and focus on analysis and optimization by automating pipelines, data storage, and visualization. This role is hybrid, based out of Austin, TX or Santa Clara, CA.
Experience Level
Senior-level. The company will evaluate candidates during the interview process and align offers to the assessed level; no specific years-of-experience requirement is stated.
Responsibilities
Key responsibilities include:
- Design, build, and maintain benchmarking automation and CI pipelines to run SPEC and real-world workloads across RISC-V silicon, FPGA/emulation platforms, and performance models.
- Implement and operate SimPoint generation and management infrastructure.
- Collect performance data into databases and build dashboards/visualizations to surface trends and regressions without manual effort.
- Develop workload capture and replay tooling (QEMU- and CRIU-based checkpointing) to enable reproducible tracing and analysis.
- Operate and maintain lab machines, clusters, and flaky hardware platforms used for performance testing.
- Collaborate closely with performance and software engineers to remove infrastructure friction and streamline workflows.
Requirements
Must-have skills and qualifications:
- Strong Linux systems engineering experience; comfortable managing lab machines, clusters, and unreliable hardware.
- Proficient in Python and shell scripting.
- Experience with CI systems (GitLab) and container technologies.
- Proven experience automating at scale: job scheduling, artifact management, databases, and dashboarding.
- Practical experience integrating benchmarking tools and running workloads on hardware, emulation, or models.
- Ability to collaborate across teams and take ownership of infrastructure components.
- Willingness and ability to work in a hybrid location (Austin, TX or Santa Clara, CA) and comply with access requirements for export-controlled technology.
Nice-to-have:
- Familiarity with CPU performance tooling and metrics (SimPoint, perf, SPEC).
- Experience with QEMU, CRIU, FPGA or emulation platforms.
- Interest in CPU performance and microarchitecture (deep microarchitecture expertise not required).
Education Requirements
Not specified.
About the Company
Company: Tenstorrent
Headquarters: Austin, Texas, United States
Tenstorrent is a technology company focused on designing innovative computing solutions. They are known for their expertise in the development of advanced hardware, including ASICs and SoCs, aimed at enhancing performance and efficiency in various applications.
