Senior ML Performance Engineer: LLM Benchmarking & GPU

Amadeus Search; San Francisco (CA); Hybrid; USD 120,000 - 160,000; Full time

Benefits offered by this job

Competitive salary

Equity and bonus opportunities

Medical, dental, and vision coverage

Retirement savings plan

Additional wellness benefits

Job summary

A leading AI infrastructure company is seeking a Senior ML Performance Engineer to design a comprehensive performance testing platform for large language models. This role requires a minimum of 7 years in performance engineering and strong experience with GPU programming and ML inference workloads. Candidates should have expertise in Python and C/C++. The position offers competitive compensation, equity, and wellness benefits in a hybrid work environment.

Qualifications

• 7+ years in performance engineering or benchmarking roles.
• Strong knowledge of ML inference workloads.
• Experience building performance testing infrastructure from scratch.

Responsibilities

• Design and implement a performance testing platform for LLM inference workloads.
• Define benchmarking methodologies and metrics.
• Collaborate with engineers to integrate performance testing.

Skills

Performance engineering

Benchmarking

ML inference

Python

C/C++

GPU optimization

Analytical skills

Tools

CUDA

ROCm

PyTorch

TensorFlow

ONNX Runtime

Job description

A leading AI infrastructure company is seeking a Senior ML Performance Engineer to design a comprehensive performance testing platform for large language models. This role requires a minimum of 7 years in performance engineering and strong experience with GPU programming and ML inference workloads. Candidates should have expertise in Python and C/C++. The position offers competitive compensation, equity, and wellness benefits in a hybrid work environment.