AI Optimization Engineer
Core
Develop and optimize software for AI and data center applications, improving performance of key benchmarks and new product introductions.
Role type
Senior IC software engineer (AI optimization)
Builds
Optimized software libraries and kernels for AMD hardware
Domain
AI / High-performance computing / Semiconductor
Deliverable
production ML models
Required skills
C, C++, Python, AI operations libraries (flashInfer, tensorRT-LLM, CUTLASS, Aiter), Triton compiler backend, CUDA/Triton/Gluon kernel implementation, roofline performance analysis, profiling tools (Nsight, ROCprofiler)
Preferred skills
AMD CNDA/RDNA SIMD/arch knowledge, kernel development on AMD platform
Technologies
flashInfer, tensorRT-LLM, CUTLASS, Aiter, Triton, llir, ASM, CUDA, Nsight, ROCprofiler
Responsibilities
Develop and drive execution of comprehensive software for new technology projects; Provide technical support for key customer projects; Develop and validate optimization features; Contribute to future architecture design for scalable systems; Collaborate with dev teams and Project Managers; Use AI agent tools to assist testing and analysis work.
Seniority
Senior, hands-on IC
