Principal Software Engineer, AI/GPU Performance

AMD; Santa Clara (CA); On-site; USD 190,000 - 260,000; Full time

Benefits offered by this job

AMD benefits

Job summary

AMD is seeking a strategic software engineering lead to enhance the performance of key applications and benchmarks. This role requires driving complex issues with cross-functional teams and translating customer feedback into AMD's AI roadmap.

The ideal candidate will lead technically, collaborate with customers, and contribute hands-on to production projects, applying expertise in GPU/CPU performance and modern LLM serving frameworks.

Qualifications

• Bachelor’s/Master’s/Ph.D. in CS/CE/EE or equivalent.
• Strong C/C++ and Python coding skills.
• Experience with CUDA or HIP GPU kernel programming.
• Familiarity with modern LLM serving frameworks (e.g., vLLM, SGLang).
• Experience implementing/optimizing attention and KV-cache on GPUs.

Responsibilities

• Understand customer requirements and identify opportunities for AMD value.
• Close gaps in the software stack to support customer solutions.
• Optimize GPU accelerator primitives (NCCL/RCCL) as needed.
• Develop hands-on with customers from PoC to production.
• Translate customer needs into actionable feedback for AMD AI roadmap.
• Leverage AI to improve productivity and workflows.
• Stay current on software/hardware trends relevant to algorithms/architecture.

Skills

C/C++

Python

CUDA

HIP

LLM serving

Client engagement

Open source

Code optimization

Education

Bachelor's/Master's/PhD in CS/CE/EE

Tools

CUDA toolkit

HIP toolkit

Job description

AMD is seeking a strategic software engineering lead to enhance the performance of key applications and benchmarks. This role requires driving complex issues with cross-functional teams and translating customer feedback into AMD's AI roadmap.

The ideal candidate will lead technically, collaborate with customers, and contribute hands-on to production projects, applying expertise in GPU/CPU performance and modern LLM serving frameworks.