Senior Inference Performance & Benchmarking Analyst

Cerebras; Sunnyvale (CA); On-site; USD 130,000 - 160,000; Full time

Job summary

An innovative AI technology company in Sunnyvale, California, is seeking a Senior Performance Analyst to join their Product team. The ideal candidate will have over 5 years of experience in ML systems and deep knowledge of open-source inference frameworks. Responsibilities include designing benchmarks for inference performance and maintaining pricing models for competitive analysis. This role is critical in ensuring the company remains competitive in AI technology and applications. Join a team that values breakthrough innovations and offers a non-corporate work culture.

Qualifications

• 5+ years of experience in ML systems, ML research engineering, or HPC.
• Deep practical experience with open-source inference frameworks.
• Strong understanding of LLM inference economics and transformer model internals.

Responsibilities

• Design benchmark suites for inference workloads.
• Stay current with GPU optimization communities.
• Build and update a competitive pricing model.
• Monitor industry announcements and pricing changes.
• Collaborate with teams to identify competitive advantages.

Skills

Open-source inference frameworks

ML systems

High-performance computing

Transformer architecture

GPU optimization

Tools

CUDA

Triton

TensorRT-LLM

Job description

An innovative AI technology company in Sunnyvale, California, is seeking a Senior Performance Analyst to join their Product team. The ideal candidate will have over 5 years of experience in ML systems and deep knowledge of open-source inference frameworks. Responsibilities include designing benchmarks for inference performance and maintaining pricing models for competitive analysis. This role is critical in ensuring the company remains competitive in AI technology and applications. Join a team that values breakthrough innovations and offers a non-corporate work culture.