Senior Performance Engineer - AI Fabric & GPU Scale

Astera Labs

San Jose (CA)

On-site

USD 135,000 - 170,000

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Job summary

Astera Labs in San Jose, CA is seeking a Senior Performance Engineer to define how we measure scale-up fabric performance and to quantify our performance leadership on real AI workloads running on GPUs at scale.

You will build roofline models, benchmarks, and end-to-end workload studies that influence architecture, firmware, and product decisions while shaping our marketing narrative in AI connectivity.

Qualifications

  • Bachelor's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field.
  • 2–5 years of industry experience in performance or systems engineering.
  • Experience running AI/ML workloads on GPU clusters with benchmarking and tuning.

Responsibilities

  • Define how the world measures scale-up fabric performance and build roofline models.
  • Develop and maintain baseline performance benchmarks using NVBandwidth and NCCL across GPU configurations.
  • Quantify impact of fabric features (e.g., Hypercast, In-Network Computing) against baselines.
  • Run end-to-end inference workloads to capture real-world performance beyond benchmarks.
  • Evaluate fabric performance as inference cluster size scales (16–32 GPUs and beyond).
  • Design head-to-head performance comparisons against competing fabric solutions.

Skills

AI/ML workloads knowledge
GPU systems
PCIe/Ethernet fundamentals
Python scripting
Performance analysis

Education

Bachelor's degree in Computer Engineering, Computer Science, Electrical Engineering, or related field

Tools

NVBandwidth
NCCL
CUDA
MPI

Job description

Astera Labs in San Jose, CA is seeking a Senior Performance Engineer to define how we measure scale-up fabric performance and to quantify our performance leadership on real AI workloads running on GPUs at scale.

You will build roofline models, benchmarks, and end-to-end workload studies that influence architecture, firmware, and product decisions while shaping our marketing narrative in AI connectivity.

Get your free, confidential resume review.
or drag and drop your file here.
Similar jobs

Similar jobs worth comparing

Senior AI Fabric Performance Engineer
Senior AI Fabric Performance Engineer

PVH (Tommy Hilfiger/Calvin Klein) • San Jose (CA)

On-site
USD 150,000 - 190,000
Performance Engineer
Performance Engineer

Asteralabs • San Jose (CA)

On-site
USD 150,000 - 190,000
Performance Engineer
Performance Engineer

Astera Labs • San Jose (CA)

On-site
USD 135,000 - 170,000
Senior AI Performance Engineer – GPU & DL
Senior AI Performance Engineer – GPU & DL

Jobtailor • California (MO)

On-site
USD 180,000 - 280,000
Scale-Up Fabric Modeling & Performance Engineer
Scale-Up Fabric Modeling & Performance Engineer

Socket.dev • San Jose (CA)

On-site
USD 185,000 - 240,000
Senior Performance Engineer — AI Scale & Efficiency
Senior Performance Engineer — AI Scale & Efficiency

NVIDIA • Washington

On-site
USD 224,000 - 432,000
Equity
Benefits
AI Infrastructure Architect: Rack-Scale Firmware & Systems
AI Infrastructure Architect: Rack-Scale Firmware & Systems

Asteralabs • North Carolina

On-site
USD 150,000 - 200,000
Senior AI Infra Performance & Observability Engineer
Senior AI Infra Performance & Observability Engineer

Coreweave • United States

On-site
USD 182,000 - 242,000
Medical, dental, and vision insurance
401(k) with employer match
Flexible PTO
+4
Senior AI Systems Performance Engineer
Senior AI Systems Performance Engineer

NVIDIA • Austin (TX)

On-site
USD 272,000 - 432,000
Equity
Benefits
Senior Performance Engineer for Scalable AI Workloads
Senior Performance Engineer for Scalable AI Workloads

NVIDIA • Oregon (WI)

On-site
USD 224,000 - 432,000
Equity
Benefits