AI Inference Performance & Scale Engineer

AMD; San Jose (CA); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Benefits at a glance

Job summary

AMD in San Jose, CA seeks a performance-obsessed engineer to drive AI inference performance on AMD GPUs. Lead a small team, profile and optimize models end-to-end, and uplift customer engagements with measurable results.

You will diagnose kernel-level bottlenecks, optimize multi-node distributed inference, and upstream efforts to open-source frameworks while collaborating with customers and internal teams.

Qualifications

• Hands-on experience profiling AI workloads end-to-end.
• Strong knowledge of GPU kernel performance and occupancy.
• Experience with AI serving frameworks and custom kernels.
• Ability to diagnose bottlenecks from user requests to kernels.
• Excellent English communication and customer-facing leadership.

Responsibilities

• Drive end-to-end performance optimization across the stack for leading models.
• Profile, diagnose, and resolve cross-stack bottlenecks from GPU kernels to scheduling.
• Lead customer-facing technical engagements and present optimization results.
• Integrate and optimize custom kernels within serving frameworks.
• Improve distributed inference performance across multi-node deployments.
• Develop and refine reusable performance optimization methodologies.
• Leverage AI agents to accelerate daily work and define best practices.

Skills

GPU computing

Python

C++

Performance profiling

AI systems

Linux

Education

Bachelor's degree in CS/CE

Advanced degree preferred

Tools

CUDA

Triton

Gluon

PyTorch

SGLang

Job description

AMD in San Jose, CA seeks a performance-obsessed engineer to drive AI inference performance on AMD GPUs. Lead a small team, profile and optimize models end-to-end, and uplift customer engagements with measurable results.

You will diagnose kernel-level bottlenecks, optimize multi-node distributed inference, and upstream efforts to open-source frameworks while collaborating with customers and internal teams.