Software Engineer – ML Kernels & Runtime

At Graphcore, we’re building the future of AI compute. We’re a team of semiconductor, software and AI experts, with deep experience in creating the complete AI compute stack - from silicon and software to infrastructure at datacenter scale. As part of the SoftBank Group, backed by significant long-term investment, we are delivering key technology into the fast-growing SoftBank AI ecosystem. To meet the vast and exciting AI opportunity, Graphcore is expanding its teams around the world. We are bringing together the brightest minds to solve the toughest problems, in a place where everyone has the opportunity to make an impact on the company, our products and the future of artificial intelligence As a Software Engineer you will be responsible to safeguard the correctness, reliability, and performance of numerical libraries. You’ll design and own end-to-end test strategies across native C++ components and validating low-level kernels. The Team The Team This is an exciting opportunity to join an expanding team at Graphcore. Kernel Engineering team is responsible for delivering high performance compute library to help customers gain the maximum performance from AI hardware. Own existing tests coverage and contribute towards improving it Improve correctness of existent microbenchmarks, regression tests, validation techniques Mentor colleagues within the team, sharing knowledge and providing guidance where appropriate Actively engage in and support Agile ways of working within the team Debug issues, resolve bugs and generally improve the quality and functionality of the product Candidate Profile Candidate Profile Essential: Strong C/C++ and Python coding skills and solid Linux fundamentals Experience testing numerical/performance-sensitive code Understanding of processor architectures and profiling on Linux Hands-on with reproducibility/determinism, tolerance design, and benchmarking Possess excellent written and oral communication skills, good work ethics, high sense of team-work Desirable: Experience benchmarking and optimising algorithmic performance, with deep understanding of memory hierarchy (cache/NUMA), multithreading (synchronisation, work partitioning) Experience of testing mixed-precision policies (FP32/BF16/FP16/FP8) and stochastic rounding Property-based testing with tensor-shape/dtype/layout generators Experience testing HPC kernels, ML runtimes/kernels, or similar ABI/API stability and packaging for Linux distros, manylinux, wheels Hands-on testing for ML frameworks - custom operators/extensions, seeds/determinism, and debugging dispatcher issues.