Senior Software Engineer (AI Compute Libraries & Performance)

Join Graphcore as a Senior Software Engineer, where you'll develop high-performance AI compute libraries for next-generation AI hardware. You'll work on linear algebra, tensor operations, numerical correctness, and low-level performance optimization. This role offers flexible working arrangements, private medical insurance, a pension plan, income protection, and opportunities for career progression and personal development.

• Design and implement kernels for linear algebra and tensor operations in C++, ensuring high performance and numerical correctness.
• Own performance and correctness by adding microbenchmarks, regression tests, and numerics validation, and profile and optimize for next-generation AI hardware.
• Mentor colleagues within the team, sharing knowledge and providing guidance, and actively engage in Agile ways of working.
• Excellent programming and scripting skills using C++ and Python
• Possess excellent written and oral communication skills, good work ethics, high sense of team-work
• Love to produce quality work and be a team player
• Understanding of processor architectures and profiling on Linux
• Strong command of algorithmic performance - vectorisation, memory hierarchy, threading, lock-free patterns
• Comfort with CPU micro-optimisations and numerical stability/trade-offs across FP32/FP16/BF16/FP8
• Hands-on with at least one BLAS/DNN stack and able to read/extend kernels
• ABI/API stability and packaging for Linux system (manylinux, wheels)
• Experience integrating native code into PyTorch or similar (custom ops, extensions, dispatch keys)