MLPerf Benchmarking Engineer

Project

Work done for a product or program.

• Optimise submission code paths within MLCommons rules.
• Analyse competitor submissions and report strengths and gaps.

Function

Work that keeps the discipline running: methods, tools, suppliers and people.

• Prepare and run MLPerf Training, Inference and Client submissions on reference systems.
• Work with the MLCommons working groups on benchmark rules and new workloads.
• Validate results through the audit and review process.
• Automate benchmark pipelines so results are reproducible across releases.
• Publish tuning notes and performance briefs for sales and marketing.

Project

1. Produce and hand over the role's key deliverables
   • MLPerf submissions
   • Reproducible benchmark harnesses
   • Competitive analysis briefs
   • Rules-compliance documentation
2. Support programsGeneral
   • Agree what each program needs
   • Deliver in time for milestones
3. Manage issuesGeneral
   • Track requests to closure
   • Escalate risks

Function

1. Run the functionGeneral
   • Maintain policies and processes
   • Keep records and controls
2. ImproveGeneral
   • Report performance
   • Lead improvement work