below marketmost similar roles pay hereabove market
This role pays more than
82%
of similar roles. Most pay
$171,330–$238,975
— the blue band above.
At the midpoint, this role pays about
$245k
versus about
$205k
for comparable roles.
Based on 240 similar postings.
Employer
About Samsung Semiconductor
Samsung Semiconductor is the global semiconductor business unit of Samsung Electronics, designing and manufacturing memory chips, logic semiconductors, and foundry solutions for a broad range of applications.
Samsung Semiconductor currently has
36 open roles
on FindRole.
Listed pay typically runs
$163,000–$253,000
across 36 roles with salary data.
The Senior Staff Performance Engineer joins the AGI Computing Lab to address system-level challenges for future AI/ML workloads. You will build and operate production AI environments, including agentic workflows, distributed inference, and MoE deployments. Daily responsibilities involve collecting workload traces and runtime telemetry to identify compute, memory, and scheduling bottlenecks across the software stack. You will define performance evaluation methodologies and communicate findings to hardware architects and software researchers. The role requires expertise in the LLM software stack, including attention and KV-cache management, and experience profiling NVIDIA GPU platforms using Nsight Systems and Nsight Compute. You must be proficient with AI frameworks such as PyTorch, vLLM, SGLang, TensorRT-LLM, DeepSpeed, Ray, or Megatron-LM to optimize multi-node AI deployments and scaling behavior.
Build and operate AI environments for production workloads like agentic workflows and MoE deployments.
Collect workload traces, runtime telemetry, and performance data across the software stack.
Identify compute, memory, communication, and scheduling bottlenecks across applications and hardware.
Communicate technical findings to hardware architects and software researchers through reports and reviews.
Define performance evaluation methodologies and benchmarking standards for hardware and software teams.
Set the technical direction for workload characterization across various platforms.
What we're looking for
Hold a BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent industry experience.
Possess 10+ years of experience with a BS, 8+ years with an MS, or 5+ years with a PhD in performance engineering, AI systems, distributed systems, or high-performance computing.
Ability to interpret workload traces, runtime telemetry, and performance data to identify and explain underlying bottlenecks in software and hardware layers.
Knowledge of the LLM software stack, including serving, scheduling, attention/KV-cache management, kernel launch, and collective communication.