> Markdown version of [/jobs/ext/4450712-senior-staff-performance-engineer](https://www.wearedevelopers.com/jobs/ext/4450712-senior-staff-performance-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Senior Staff Performance Engineer

- **Company:** Samsung
- **Location:** San Jose, CA, United States
- **Experience:** Expert
- **Salary:** $189,000.0 - $301,000.0
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Systems Engineering, Profiling, Computer Engineering, Distributed Systems, High Performance Computing, Pytorch, DeepSpeed, Large Language Models, Information Technology, Deployment Automation, SGLang, TensorRT, VLLM, Megatron
- **Published:** October 7, 2026
- **Apply:** https://jobs.localjobnetwork.com/apply/add/88543817/1

## About the Role

* BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent industry experience. Required industry 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.
 * Ability to interpret workload traces, runtime telemetry, and performance data to identify bottlenecks and explain their underlying causes, including how workload characteristics interact with specific operations and mechanisms within software and hardware layers.
 * Knowledge of the LLM software stack, including serving and scheduling, attention and KV-cache management, kernel launch and memory-transfer overhead, and collective communication, and how these interact with accelerator compute throughput, memory hierarchy, memory bandwidth, and interconnect topology.
 * Experience characterizing agentic workflows, long-context processing, MoE models, or disaggregated inference deployments.
 * Experience profiling and optimizing AI workloads on NVIDIA GPU platforms using Nsight Systems and Nsight Compute, with analysis informed by GPU execution, memory hierarchy, and communication mechanisms.
 * Experience analyzing multi-node AI deployments, including synchronization overhead, load imbalance, communication patterns, and scaling behavior.
 * Experience with AI frameworks or serving systems such as PyTorch, vLLM, SGLang, TensorRT-LLM, DeepSpeed, Ray, or Megatron-LM.

## Description

Location: Daily onsite presence at our San Jose, CA office / U.S. headquarters in alignment with our Flexible Work policy.

What You'll Do

 * Build and operate AI environments that reflect production workloads, including agentic workflows, distributed inference, disaggregated serving architectures, and MoE deployments.
 * Collect workload traces, runtime telemetry, and performance data across the software stack from AI applications.
 * Characterize and compare workloads across environments and platforms, identifying compute, memory, communication, and scheduling bottlenecks from applications and frameworks to runtimes, hosts, and devices.
 * Communicate findings to hardware architects, systems engineers, and software researchers through reports, presentations, and architecture reviews.
 * Define performance evaluation methodologies and benchmarking standards for adoption across hardware and software teams, and set the technical direction for workload characterization., At Samsung Semiconductor, we use Artificial Intelligence (AI) tools in the recruitment process to enhance efficiency. However, AI is used as a support tool, not a final decision-maker. All hiring decisions are made by our human recruiting team and hiring managers to ensure every candidate is evaluated fairly and holistically.