Graphcore
Staff AI Performance Engineer
Milpitas, California, United States · Staff · Full-time · Posted Oct 9, 2026
About the job
Leads analysis and optimization of distributed AI training and inference workloads to improve performance, efficiency, scalability, and reliability at data center scale.
What you'll do
- Lead performance workstreams across hardware and software, identifying bottlenecks and validating improvements.
- Build benchmarks, profile demanding workloads, and develop tools for performance analysis and optimization.
- Coordinate investigations across teams and use performance evidence to guide engineering decisions.
What they ask for
- Strong experience profiling and optimizing AI, machine learning, or high-performance computing workloads.
- Experience with distributed systems and communication libraries such as MPI, NCCL, UCX, or libfabric.
- Strong C++ and Python skills, including reliable tools or performance-sensitive software.
- Deep understanding of compute, memory, and communication behavior in large-scale systems; ability to lead complex technical work across teams.
Nice to have
- Familiarity with MLPerf, accelerated architectures, ML frameworks, or high-performance interconnects.
Tools
C++, Python, MPI, NCCL, UCX, libfabric, MLPerf
AI focus
Optimizes AI training and inference workloads across distributed systems.
Model-written summary · the original posting is authoritative