Staff AI Performance Engineer: Distributed HPC on ARM

Graphcore; Austin (TX); On-site; USD 100,000 - 150,000; Full time

Benefits offered by this job

Medical, dental, and vision coverage

401(k) retirement plan

Flexible Spending Accounts (FSAs)

Health Savings Accounts (HSAs)

Employee Assistance Programme (EAP)

Job summary

Graphcore in Austin, Texas is seeking a skilled engineer to optimize performance across ARM-based architectures and large-scale distributed systems. This role will engage with the System Engineering Performance team to enhance AI workloads effectively.

The ideal candidate will have a BS/MS in a related field, alongside strong programming skills in C++ and Python, as well as experience with distributed systems and HPC optimizations. Graphcore offers flexible working and a comprehensive benefits package to support your health and wellbeing.

Qualifications

• Experience with profiling and optimizing HPC or AI/ML workloads.
• Familiarity with ML benchmarks such as MLPerf.
• Understanding of ARM architectures and toolchains.

Responsibilities

• Analyze ML models’ compute and memory requirements using roofline analysis and simulations.
• Collaborate across hardware and software teams to optimize large-scale AI workloads.
• Benchmark, monitor, and troubleshoot system performance across distributed systems.
• Develop high-quality, ARM-compatible code and documentation.

Skills

C++

Python

Distributed systems

Communication libraries (MPI, NCCL, UCX)

HPC or AI/ML workload optimization

Education

BS/MS in Computer Science, Electrical Engineering, or related field

Tools

ML frameworks (e.g., PyTorch, TensorFlow)

HPC networking technologies (InfiniBand, RoCE)

Job description

Graphcore in Austin, Texas is seeking a skilled engineer to optimize performance across ARM-based architectures and large-scale distributed systems. This role will engage with the System Engineering Performance team to enhance AI workloads effectively.

The ideal candidate will have a BS/MS in a related field, alongside strong programming skills in C++ and Python, as well as experience with distributed systems and HPC optimizations. Graphcore offers flexible working and a comprehensive benefits package to support your health and wellbeing.