Principal AI Performance Engineer

Join Graphcore, a leading AI technology company, as a Principal AI Performance Engineer. In this role, you will define the performance direction for large-scale AI systems, shape decisions across hardware, software, networking, and system architecture, and lead complex performance investigations. You will have a significant influence on AI infrastructure at a data center scale, and the position is based in Austin, Texas.

- Definir y establecer la dirección de rendimiento para sistemas de IA a gran escala, influyendo en decisiones de hardware, software y arquitectura del sistema. - Liderar investigaciones de rendimiento complejas, desde el comportamiento del modelo hasta la escalabilidad en múltiples nodos, y convertir la evidencia en hojas de ruta técnicas. - Establecer estándares de medición, guiar la estrategia de comunicación distribuida y revisar herramientas críticas en C++ y Python.

- Expert understanding of compute, memory, communication and scaling behavior in distributed systems - Expert C++ and Python skills, including reliable tools or performance-sensitive software - Proven technical leadership across complex performance-engineering or system-architecture initiatives - Ability to define benchmarks, measurement practices or optimization standards across teams - Deep experience profiling and optimizing AI, machine learning or high-performance computing workloads at scale - Experience with MPI, NCCL, UCX, libfabric, MLPerf, accelerated architectures or high-performance interconnects