Back
Specialized senior role but strong AMD brand and metro location create moderate competition.
Highly specialized GPU and benchmarking expertise limits transferability across industries.
Explicit 8+ years, GPU benchmarking expertise, tooling experience and degree requirements create strict shortlisting filters.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Lead measurement and characterization of Data Center GPU (DCGPU) system performance across AI workloads including training, inference, and microbenchmarks.
Define, enforce, and standardize reproducible performance measurement methodologies addressing system variability, software stacks, and configurations.
Develop and enhance performance measurement tools and automation; collaborate cross-functionally to deliver accurate, reliable performance insights for engineering and business decisions.
8–12+ years of experience in performance measurement, benchmarking, or system characterization, particularly with AI workloads on GPU or complex SoC systems.
Proven expertise in running and analyzing AI workloads (LLMs, training/inference) on GPU systems with focus on reproducibility and methodological rigor.
Proficiency with performance profiling and measurement tools (e.g., rocprof, Nsight, perf) and programming/scripting skills in Python, C/C++, or similar for automation.
Bachelor’s or Master’s degree in Computer/Electrical Engineering, Computer Science, or related field.
Experienced technical leader with deep expertise in system-level performance benchmarking in AI/GPU environments and a strong focus on data accuracy and reproducibility.
Detail-oriented operator skilled in experimental validation, cross-checking results, and continuous improvement of measurement infrastructure and tooling.
Collaborative partner with ability to work closely with tools teams and cross-functional stakeholders to align methodologies and improve measurement workflows.