Samsung
Senior Staff Performance Engineer
$189K–$301K
San Jose, California, United States · Senior Staff · Full-time · Posted Sep 29, 2026
- Experience
- 10+ years with a BS, 8+ years with an MS, or 5+ years with a PhD in performance engineering, AI systems, distributed systems, high-performance computing, or a related area. Candidates with additional experience and a record of technical leadership across teams may be considered at the Senior Staff level.
- Education
- BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent industry experience.
About the job
Builds and operates production-like AI workload environments, analyzes performance across software and hardware layers, and establishes benchmarking methods to guide platform design.
What you'll do
- Operate AI environments for agentic workflows, distributed inference, disaggregated serving, and MoE deployments; collect traces and telemetry.
- Characterize workloads and identify compute, memory, communication, and scheduling bottlenecks across the software stack and devices.
- Communicate findings to technical teams and define performance evaluation methodologies and benchmarking standards.
What they ask for
- BS, MS, or PhD in a related field, or equivalent industry experience.
- Ability to analyze workload traces, runtime telemetry, and performance data to identify and explain bottlenecks.
- Knowledge of the LLM software stack and its interactions with accelerator, memory, and interconnect systems.
- Experience profiling and optimizing AI workloads on NVIDIA GPU platforms using Nsight Systems and Nsight Compute.
Nice to have
- Experience characterizing agentic workflows, long-context processing, MoE models, or disaggregated inference deployments.
- Experience with multi-node AI deployments and frameworks or serving systems such as PyTorch, vLLM, SGLang, TensorRT-LLM, DeepSpeed, Ray, or Megatron-LM.
Pay
$189,000 — $301,000 USD (base salary)
Tools
NVIDIA GPU, Nsight Systems, Nsight Compute, PyTorch, vLLM, SGLang, TensorRT-LLM, DeepSpeed
AI focus
Performance engineering for AI/ML workloads, including production-like agentic workflows, distributed inference, disaggregated serving, and MoE deployments.
Model-written summary · the original posting is authoritative