Sr. Engineer, Performance Infrastructure (RISC-V)

Description

The company is building a high-performance RISC-V CPU from scratch and works across AI software, compilers, platforms, networking and semiconductors. Its team of technologists is growing and hiring at every seniority level.

This role builds and runs the performance infrastructure for RISC-V hardware and software, which both teams' performance work depends on. It covers benchmarking automation, data collection and workload capture on silicon, FPGA and emulation platforms, and performance models. You will work across both teams so that performance and software engineers can spend their time on analysis and optimization rather than running experiments by hand.

You will get end-to-end exposure to CPU performance work, from workload capture through analysis and convergence. You will also work hands-on with pre-silicon and post-silicon platforms, including models, emulation, FPGA and real RISC-V hardware, and integrate open-source and industry-standard tools into production flows.

Responsibilities

• Set up and keep running automated benchmarks and CI pipelines for SPEC and real-world workloads on RISC-V silicon, FPGA and emulation platforms, and performance models.
• Take charge of the infrastructure that generates and manages SimPoints.
• Build databases for performance data, with dashboards and visualization on top, so trends and regressions show up without manual effort.
• Create workload capture and replay tools using QEMU and CRIU checkpointing, so performance engineers can trace and analyze workloads reproducibly.
• Work with performance and software engineers on both teams to learn their workflows and remove the infrastructure friction they face.

Requirements

• You are good at spotting problems and designing solutions, and you take ownership of the systems you build.
• You like building tools and improving workflows so other engineers can move faster.
• You know Linux well and are comfortable with lab machines, clusters and unreliable hardware platforms.
• You write Python and shell scripts with confidence, and you have solid experience with GitLab CI and containers.
• You have experience automating at scale, including job scheduling, artifact management, databases and dashboards.
• Curiosity about CPU performance is a plus; a deep microarchitecture background is not required.

Conditions

The role is remote from the US or Australia, or hybrid from Austin, TX or Santa Clara, CA.

Candidates are assessed for the right level during interviews, and offers match that level, which may differ from the level in this posting.

Pay for all engineers ranges from $100k to $500k, including base salary and variable compensation targets. Experience, skills, education, background and location all affect the actual offer.

The role requires access to technology that needs a U.S. export license for people whose most recent country of citizenship or permanent residence is in EAR Country Groups D:1, E1 or E2. The offer depends on your eligibility to access U.S. export-controlled technology, which may depend on your citizenship or permanent residency status or on obtaining prior license approval from the U.S. Commerce Department or another applicable federal agency. If employment is not possible under U.S. export laws, the offer will be withdrawn.

The company is an equal opportunity employer.

Benefits

• The company says its compensation package and benefits are highly competitive.