Lead HPC Systems & Performance Engineer

Stanford Black Limited; Dallas (TX); On-site; USD 140,000 - 210,000; Full time

Job summary

Stanford Black Limited seeks a Lead HPC Systems & Performance Engineer to take ownership of compute performance in large-scale HPC environments. You will evaluate CPU, GPU and accelerator technologies, benchmark hardware, identify bottlenecks, and translate test data into architecture decisions.

Working with storage, networking, vendors, and customers, you''ll help build and optimize end-to-end HPC platforms across the compute stack, applying deep expertise in performance tuning and AI/ML

Qualifications

• Masters or PhD in Computer Science, Systems Engineering, or similar field.
• Strong background in HPC systems, performance engineering or systems architecture.
• Deep understanding of CPU, GPU and accelerator architectures.
• Strong knowledge of memory hierarchy, NUMA and system performance.
• Hands-on experience with Linux tuning, optimisation and performance profiling.
• Experience designing or optimising HPC clusters and parallel computing environments.
• Understanding of InfiniBand/RoCE and their impact on compute performance.
• Experience benchmarking and evaluating new hardware.
• Knowledge of distributed/parallel storage and its relationship with compute performance.
• Experience supporting demanding AI/ML, scientific computing or simulation workloads.

Responsibilities

• Own compute performance across large-scale HPC environments.
• Evaluate emerging CPU, GPU and accelerator technologies and benchmark new hardware.
• Collaborate with storage/networking, vendors, and internal teams to optimize end-to-end HPC platforms.

Skills

HPC systems

Performance engineering

Systems architecture

CPU architectures

GPU architectures

Memory hierarchy

NUMA

Linux tuning

Performance profiling

HPC clusters

Parallel computing

InfiniBand

RoCE

AI/ML workloads

NVIDIA DCGM

Nsight

MLPerf

GPU/CPU/DPU clusters

Education

Masters

PhD

Tools

DCGM

Nsight

MLPerf

Job description

Lead HPC Systems & Performance Engineer (Dallas, Texas):

The Company:

My client is a rapidly growing HPC and AI Supercompute Lab operating at the forefront of hyperscale compute.

With significant investment behind its growth, the business is building next-generation infrastructure supporting demanding AI, scientific research, simulation, and data-intensive workloads.

The Role:

They are looking for a Lead HPC Systems & Performance Engineer to take ownership of compute performance across large-scale HPC environments.

You'll evaluate emerging CPU, GPU and accelerator technologies, benchmark new hardware, identify performance bottlenecks, and turn real-world test data into architecture decisions.

Working across the compute stack, you'll collaborate with storage and networking specialists, hardware vendors, internal engineering teams and customers to build and optimise end-to-end HPC platforms.

Required Skills:

• Masters &/or PhD in Computer Science, Systems Engineering, or similar subject(s).
• Strong background in HPC systems, performance engineering or systems architecture.
• Deep understanding of CPU, GPU and accelerator architectures.
• Strong knowledge of memory hierarchy, NUMA and system performance.
• Hands-on experience with Linux tuning, optimisation and performance profiling.
• Experience designing or optimising HPC clusters and parallel computing environments.
• Understanding of InfiniBand/RoCE and their impact on compute performance.
• Experience benchmarking and evaluating new hardware.
• Knowledge of distributed/parallel storage and its relationship with compute performance.
• Experience supporting demanding AI/ML, scientific computing or simulation workloads.
• NVIDIA GPU ecosystem and tools such as DCGM, Nsight or MLPerf.
• Experience with large-scale GPU/CPU/DPU clusters & emerging/pre-production hardware.