Power and Performance Validation Engineer
Graphcore is a SoftBank-owned AI-compute company developing AI processors, systems, and software for machine-learning workloads.
Funding history
About Graphcore
Graphcore develops Intelligence Processing Units (IPUs) and the Poplar SDK for building and running machine-learning applications. It continues operating under the Graphcore name as a wholly owned SoftBank Group subsidiary.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will define and lead validation strategies for power, thermal and performance characterization. You will plan validation across projects, lead post-silicon bring-up, automate regression infrastructure in Python, run benchmarks and analyse results. You will work with engineering disciplines to resolve issues and communicate findings and risks.
Requirements
- Experience in power and performance validation, silicon characterization or system performance engineering
- Deep understanding of SoC architecture, including CPU, memory, interconnect and high-speed I/O
- Linux systems knowledge and low-level performance analysis experience
- Python programming skills for automation, orchestration and data analysis
- Experience with benchmarking and profiling tools such as stress-ng, fio, perf or iperf
- Experience debugging complex hardware and software interactions
- Ability to define validation methodologies, workload models and test strategies
- Ability to interpret large datasets and identify system bottlenecks
- Strong communication and cross-functional collaboration skills
- Ability to work independently on complex technical tasks
Responsibilities
- Define and lead validation strategies for power, thermal and performance characterization
- Plan and execute validation activities across projects and milestones
- Develop validation plans for functional, stress, workload and corner-case scenarios
- Lead post-silicon bring-up and characterization
- Validate CPU, memory, interconnect and high-speed I/O subsystems
- Develop automation frameworks, regression infrastructure and reporting tools using Python
- Design and execute benchmark workloads and performance experiments
- Debug complex hardware and software issues with cross-functional partners
- Define validation metrics, pass/fail criteria and reporting methodologies
- Analyse power, thermal and performance data to identify bottlenecks
- Communicate technical findings, status, risks and recommendations