Compute Farm & HPC Engineer (Design Computing)

Project

Work done for a product or program.

• Integrate scheduler license-aware dispatch with FlexLM counters to prevent license-starved job failures.
• Size and qualify new server generations, memory configurations and interconnects for EDA workload profiles.
• Implement cloud bursting and hybrid scheduling for peak verification regressions and signoff runs.
• Automate node health checking, drain and repair workflows to keep bad hardware out of production queues.
• Support project teams in structuring large regression and multi-corner runs for efficient farm consumption.
• Provide priority escalation handling during tapeout crunch periods with deadline-aware scheduling.

Function

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

• Configure and tune LSF, Slurm or Grid Engine queues, fair-share policies, preemption and resource reservations across thousands of nodes.
• Model and enforce job resource requirements for memory, cores and licenses so jobs do not thrash or waste slots.
• Analyse farm utilisation, queue wait times and job failure patterns and tune policy to raise effective throughput.
• Report capacity headroom and forecast compute demand against project plans and license inventory.

Project

1. Produce and hand over the role's key deliverables
   • Scheduler configuration, queue and fair-share policy
   • Farm utilisation and throughput analytics
   • Hardware qualification and sizing recommendations
   • Cloud bursting integration for peak workloads
   • Compute capacity forecast tied to project roadmap
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