Senior External GPU & ASIC Performance Modeling Engineer

General Diffusion, Inc.

San Francisco (CA)

Hybrid

USD 180,000 - 290,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

General Diffusion, Inc. in San Francisco seeks a Member of Technical Staff to develop portable measurements and predictive performance models for external GPUs and ASICs, covering compute, memory, data movement, and contention.

You will produce traceable, evidence-backed capability profiles for compute-world-model, compiler, and runtime partners. The role emphasizes calibrating models to measurements, designing repeatable experiments, and collaborating with GPU Systems & Fabric on multi-device

Qualifications

  • Experience in accelerator architecture or performance modeling grounded in measured GPU, inference-ASIC, or comparable heterogeneous-system behavior.
  • Ability to design benchmarks that combine focused microkernels with representative workloads, control confounding variables, and make results reproducible.
  • Demonstrated model-to-measurement correlation work, including calibration, error analysis, and clear treatment of uncertainty under workload or architecture shift.
  • Fluency with performance-profiling methods and the interaction of arithmetic intensity, memory hierarchy, occupancy or utilization, and data movement.
  • Vendor-neutral hardware–software judgment: able to compare capabilities through evidence rather than feature lists, and communicate limits to systems and ML collaborators.

Responsibilities

  • Design controlled microbenchmarks and workload-level experiments that isolate compute throughput, memory-hierarchy behavior, data movement, and contention on external GPU and ASIC targets.
  • Build repeatable characterization protocols that record workload, hardware, software, configuration, and measurement conditions so comparisons across targets are traceable.
  • Develop and validate performance models against measured behavior; quantify prediction error, uncertainty, and the conditions under which a model transfers or ceases to transfer.
  • Use profiler evidence and end-to-end measurements to distinguish compute, memory, communication, and interference limits rather than treating peak specifications as attainable performance.
  • Publish decision-ready capability profiles and methodological caveats for compute-world-model, compiler, and runtime partners, including the evidence behind each conclusion.
  • Partner with GPU Systems & Fabric on multi-device measurements and incorporate relevant data-movement characteristics into profiles, while leaving collective and fabric optimization to that team.

Skills

Accelerator architecture
Performance modeling
Benchmark design
Profiling methods
Data movement

Job description

Member of Technical Staff, GPU & ASIC Performance Modeling

Understand external GPUs and ASICs through portable measurements and predictive performance models.

Status Open

Area Hardware Research

Develop portable measurements and predictive performance models that explain how externally available GPUs and ASICs behave under representative workloads, including compute, memory, data movement, and contention. Turn that evidence into calibrated capability profiles that help compute-world-model, compiler, and runtime teams reason about unlike targets—without owning kernel implementation, compiler lowering, placement policy, or silicon design.

01 / The work

What you’ll work on
  • Design controlled microbenchmarks and workload-level experiments that isolate compute throughput, memory-hierarchy behavior, data movement, and contention on external GPU and ASIC targets.
  • Build repeatable characterization protocols that record workload, hardware, software, configuration, and measurement conditions so comparisons across targets are traceable.
  • Develop and validate performance models against measured behavior; quantify prediction error, uncertainty, and the conditions under which a model transfers or ceases to transfer.
  • Use profiler evidence and end-to-end measurements to distinguish compute, memory, communication, and interference limits rather than treating peak specifications as attainable performance.
  • Publish decision-ready capability profiles and methodological caveats for compute-world-model, compiler, and runtime partners, including the evidence behind each conclusion.
  • Partner with GPU Systems & Fabric on multi-device measurements and incorporate relevant data-movement characteristics into profiles, while leaving collective and fabric optimization to that team.
02 / The background
What you bring
  • Experience in accelerator architecture or performance modeling grounded in measured GPU, inference-ASIC, or comparable heterogeneous-system behavior.
  • Ability to design benchmarks that combine focused microkernels with representative workloads, control confounding variables, and make results reproducible.
  • Demonstrated model-to-measurement correlation work, including calibration, error analysis, and clear treatment of uncertainty under workload or architecture shift.
  • Fluency with performance-profiling methods and the interaction of arithmetic intensity, memory hierarchy, occupancy or utilization, and data movement.
  • Vendor-neutral hardware–software judgment: able to compare capabilities through evidence rather than feature lists, and communicate limits to systems and ML collaborators.
03 / The evidence
What progress looks like
  • A traceable characterization suite produces repeatable capability profiles across selected external targets, with workload and environment provenance sufficient for another engineer to reproduce the comparison.
  • Validation reports compare model estimates with held-out measurements, quantify error and uncertainty by workload regime, and document transfer limits rather than obscuring mismatches.
  • Compiler, runtime, and research partners receive evidence-backed profiles that identify the relevant bottleneck or compatibility caveat for a target and cite the underlying measurements.
04 / In the system
Where this role fits

This is characterization of external silicon, not RTL chip design or ownership of a vendor roadmap.

Apply

Interested in this role?

Email your background and a short note about the work you would like to do.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Hardware Engineer (Performance Modeling)
Hardware Engineer (Performance Modeling)

Normal Computing • United States

On-site
USD 120,000 - 170,000
Sr AI/ML Performance Architect
Sr AI/ML Performance Architect

Compunnel Inc. • Milpitas (CA)

On-site
USD 150,000 - 210,000
CPU Performance Modeling (Lead & ICs)
CPU Performance Modeling (Lead & ICs)

Nuvacore • United States

On-site
USD 200,000 - 300,000
Performance Engineer
Performance Engineer

Darwin Recruitment • San Francisco (CA)

On-site
USD 170,000 - 250,000
Research Member of Technical Staff, Hardware Systems
Research Member of Technical Staff, Hardware Systems

Touchdown Labs • United States

Remote
USD 120,000 - 190,000
Hardware Engineer, Performance Modeling
Hardware Engineer, Performance Modeling

Normal Computing Corp. • Mountain View (CA)

On-site
USD 140,000 - 210,000
Senior Performance Modeling Architect, CPU Fabric and LLC
Senior Performance Modeling Architect, CPU Fabric and LLC

NVIDIA Corporation • United States

On-site
USD 152,000 - 288,000
Performance Modeling Lead
Performance Modeling Lead

OpenAI • Los Angeles (CA)

Hybrid
USD 130,000 - 180,000
Relocation assistance
Hybrid work model
Performance Architect
Performance Architect

Oho Group • San Francisco (CA)

On-site
USD 180,000 - 260,000
Graphics (GPU) Performance Modeling Engineer
Graphics (GPU) Performance Modeling Engineer

Apple Inc. • Austin (TX)

On-site
USD 90,000 - 130,000