AI Performance Engineer – HPC, ARM & Distributed Inference

EngineersOfAI; Austin (TX); On-site; USD 90,000 - 120,000; Full time

Job summary

EngineersOfAI is seeking a candidate to optimize AI workloads across various architectures. The role involves collaboration with hardware and software teams to ensure efficient performance of AI/ML models, as well as benchmarking and troubleshooting at scale.

The ideal applicant has a BS/MS in Computer Science or a related field, with strong programming skills in C++ and Python, and experience with distributed systems. This position offers opportunities to work on cutting-edge technology in Austin, Texas.

Qualifications

• Strong programming skills in C++ and Python.
• Experience with distributed systems and communication libraries.
• Experience profiling and optimizing HPC or AI/ML workloads.

Responsibilities

• Analyze ML models’ compute and memory requirements.
• Collaborate across hardware and software teams.
• Benchmark and troubleshoot system performance.

Skills

C++

Python

Distributed systems

Communication libraries (MPI, NCCL, UCX)

Profiling and optimizing HPC or AI/ML workloads

Education

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

Tools

ML frameworks (PyTorch, TensorFlow)

HPC networking technologies (InfiniBand, RoCE)

Job description

EngineersOfAI is seeking a candidate to optimize AI workloads across various architectures. The role involves collaboration with hardware and software teams to ensure efficient performance of AI/ML models, as well as benchmarking and troubleshooting at scale.

The ideal applicant has a BS/MS in Computer Science or a related field, with strong programming skills in C++ and Python, and experience with distributed systems. This position offers opportunities to work on cutting-edge technology in Austin, Texas.