Lead Performance and Optimization Engineer
Core
Lead Performance and Optimization Engineer optimizing CPU inference performance for ML workloads on AMD EPYC server CPUs.
Role type
Senior IC performance engineer (CPU/ML inference)
Builds
Optimized ML inference performance and multiinstance execution frameworks for AMD EPYC systems
Domain
Semiconductor / High-performance computing / Machine Learning
Deliverable
production ML models
Required skills
CPU microarchitecture, Linux tuning, ML inference execution, Python, Bash, performance profiling tools, thread affinity, NUMA awareness
Preferred skills
Multiinstance execution strategies, kernel/operator optimization, automation pipeline development
Technologies
EPYC, ZenDNN, PyTorch, TensorFlow, ONNX Runtime, perf, VTune, ftrace, PMU counters
Responsibilities
Optimize ML inference workloads on CPUs using EPYC-optimized libraries; Configure and tune OS/BIOS parameters (NUMA, HugePages, SMT); Design and validate thread/core affinity strategies; Develop automation pipelines for benchmarking and profiling; Analyze scaling and identify bottlenecks in compute and memory; Contribute to multiinstance execution framework development
Seniority
Senior, hands-on IC
