Senior Software Engineer - AI Compute Libraries & Performance

O projekcie:
The team and culture
You will join the ML Kernels & Runtime team, which builds high-performance compute libraries for Graphcore AI hardware. The team works through hands-on engineering, profiling data, design discussion and rapid iteration.

Engineers take ownership from kernel design through benchmarking, validation and bug resolution. Decisions are shaped by evidence, including measurements, numerical behaviour and code quality.

The team values people who think big, act fast and take responsibility for outcomes. You will be encouraged to speak up, support others and help improve how the team works.
Benefits- Flexible working: Balance your work and personal life with greater flexibility- Comprehensive healthcare and dental cover: Premium medical and dental insurance, with the option to extend cover to your family- Phantom equity: Share in Graphcore’s success- Fitness and wellbeing support: A fully funded Medicover gym card, giving you access to a wide range of gyms, fitness classes and leisure centres- Financial protection: Death and disability insurance, providing financial security for you and your loved ones- Retirement savings: Build your financial future, with a 4% employer contribution from Graphcore, alongside your own contributions- Employee Assistance Programme (EAP): Confidential advice and support for you and your family across a range of personal, financial and wellbeing matters
We welcome people from all backgrounds and experiences and are committed to building an inclusive environment where everyone can do their best work.
We’re an equal opportunity employer and recognise that everyone brings different strengths and perspectives. If you need any adjustments during the interview process, just let us know - we’re happy to support you.
Sponsorship
Applicants must have the legal right to work in Poland. Unfortunately, we are unable to provide visa sponsorship or support visa applications for this role.
Join the Team at Graphcore
Graphcore is one of the world’s leading innovators in Artificial Intelligence compute. It is developing hardware, software and systems infrastructure that will unlock the next generation of AI breakthroughs and power the widespread adoption of AI solutions across every industry.

As part of the SoftBank Group, Graphcore is a member of an elite family of companies responsible for some of the world’s most transformative technologies. Together, they share a bold vision: to enable Artificial Super Intelligence and ensure its benefits are accessible to everyone.

Graphcore’s teams are drawn from diverse backgrounds and bring a broad range of skills and perspectives. A melting pot of AI research specialists, silicon designers, software engineers and systems architects, Graphcore brings together deep expertise to solve complex problems and deliver meaningful progress in AI compute.

If you want to build the compute libraries that help Graphcore hardware deliver real AI performance, we’d love to hear from you. Apply now to be part of the journey.

Wymagania:
What we’re looking for- Strong C++ and Python skills, with experience building performance-sensitive software- Understanding of processor architectures and profiling on Linux- Experience designing or implementing kernels for linear algebra, tensor operations or related compute workloads- Strong grasp of algorithmic performance, including vectorisation, memory hierarchy, threading or lock-free patterns- Interest in numerical stability, benchmarking and trade-offs across FP32, FP16, BF16 or FP8- Clear communication skills, strong ownership and a practical team mindset

While we have outlined a set of requirements, we value transferable skills and diverse experiences. If you meet most of our essential criteria, we encourage you to submit an application and showcase how your background makes you a strong candidate.

Codzienne zadania:
- Build the compute libraries that make next-generation AI hardware perform in real workloads.
- As a Senior Software Engineer, you will build high-performance AI compute libraries for next-generation hardware. Your work will span linear algebra, tensor operations, numerical correctness and low-level optimisation.
- You will design and implement kernels for GEMM, batched GEMM, convolutions, reductions, elementwise and fused operations. You will own performance and correctness through microbenchmarks, regression tests and numerics validation.
- Your code will sit close to the hardware and influence how efficiently AI workloads run. You will profile threading, cache locality, memory layout and launch efficiency to improve performance.
- You will also debug issues, improve product quality and share knowledge with colleagues. This role is ideal for an engineer who enjoys precise, measurable impact.