onboard, measure, analyze, and optimize the performance, quality, and efficiency of AI and non-AI workloads on Intel DCG platforms, including CPU (Xeon), GPU, and NPU
Run benchmarks to measure latency, throughput, and memory usage
Identify bottlenecks and create detailed reports, dashboards, and visualizations for performance data
Build automated benchmarking pipelines to ensure reproducible results
Work with internal and external stakeholders to optimize systems based on benchmark outcomes
Requirements
Bachelor's in Computer Science, Electrical Engineering, or a related STEM field with 5+ years of relevant experience
OR Master's in Computer Science, Electrical Engineering, or a related STEM field with 3+ years of relevant experience
Hardware bring-up (OS and middleware install, network setup, BIOS configuration)
scripting (Python, shell scripting)
performance tools (e.g. Linux perf)
container technologies (Kubernetes, Docker)
OS (primarily Linux)
Ethernet and networking
AI/ML (vision AI, Gen-AI, VLM, VLA) understanding with evaluation experience
experience with ML frameworks (PyTorch, OpenVINO,vLLM, TensorFlow) and AI benchmarking.