Senior Staff Performance Engineer

Description

The team builds scalable computing platforms for future AI and ML workloads, meeting their compute and memory needs while cutting energy use and raising performance.

The team works alongside hardware and software engineers to find the challenges AI and ML workloads create and to test new computing abstractions that balance hardware and software.

The team also researches emerging work in memory, computing, interconnect, and AI and ML so its platforms can handle demanding future workloads.

Responsibilities

• Set up AI environments that mirror production workloads, such as agentic workflows, distributed inference, disaggregated serving, and MoE deployments.
• Capture workload traces, runtime telemetry, and performance data from AI applications across the full software stack.
• Compare workloads across environments and platforms, and pinpoint bottlenecks in compute, memory, communication, and scheduling, from applications and frameworks down to runtimes, hosts, and devices.
• Share findings with hardware architects, systems engineers, and software researchers through reports, presentations, and architecture reviews.
• Define performance evaluation methods and benchmark standards that hardware and software teams can adopt, and guide the technical direction of workload characterization.

Requirements

• Hold a BS, MS, or PhD in computer science, computer engineering, electrical engineering, or a related field, or have equivalent industry experience. Required industry experience is 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 more experience and a record of technical leadership across teams may be considered at the Senior Staff level.
• Read workload traces, runtime telemetry, and performance data to find bottlenecks and explain their root causes, including how a workload interacts with specific operations and mechanisms in software and hardware.
• Understand 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 affect accelerator throughput, memory hierarchy, memory bandwidth, and interconnect topology.
• Have experience characterizing agentic workflows, long-context processing, MoE models, or disaggregated inference deployments.
• Have experience profiling and optimizing AI workloads on NVIDIA GPUs with Nsight Systems and Nsight Compute, interpreting results through GPU execution, memory hierarchy, and communication mechanisms.
• Have experience analyzing multi-node AI deployments for synchronization overhead, load imbalance, communication patterns, and scaling behavior.
• Have experience with AI frameworks or serving systems such as PyTorch, vLLM, SGLang, TensorRT-LLM, DeepSpeed, Ray, or Megatron-LM.

Conditions

Work on site daily at the San Jose, CA office, which serves as the U.S. headquarters, in line with the company's Flexible Work policy.

Base pay ranges from $189,000 to $301,000 USD for this level across all US locations and functions. Actual pay depends on work location, job-related knowledge, skills, and experience.

Benefits

• Incentive pay tied to individual and company performance.
• Medical, dental, vision, and 401k coverage, plus a wellbeing-focused rewards plan.
• A charitable giving match and regular volunteering opportunities.
• Paid time off of 4+ weeks per year, plus holidays and sick leave.
• A stipend for fertility care or adoption, caregiver support, and medical travel support.
• On-demand apps and free confidential therapy sessions.
• An onsite café and gym, plus virtual fitness classes.
• A flexible environment that helps you balance work and life.