Senior Software Engineer - AI Compute Libraries & Performance

Graphcore; Deutschland; Hybrid; EUR 90.000 - 150.000; Vollzeit

Benefits dieser Stelle

Unlimited annual leave

Pension matching

Phantom equity

Flexible work location

Collaboration spaces

Free food & on-site barista

Health cash plan

Income protection

Life assurance

Private medical insurance

Zusammenfassung

Graphcore in Germany seeks a Senior Software Engineer to build high-performance AI compute libraries close to hardware, owning kernels for GEMM, convolutions, reductions, and fused ops. You will optimize performance, ensure numerical reliability, and mentor teammates within the ML Kernels and Runtime team, working with C++ and Python on Linux.

You will join a team that values ownership, fast technical feedback, and real outcomes for AI workloads.

Qualifikationen

• Strong C++ and Python programming skills.
• Understanding of processor architectures and profiling on Linux.
• Excellent written and oral communication; good teamwork.

Aufgaben

• Design and implement kernels for linear algebra and tensor ops (GEMM, batched GEMM, convolutions, reductions, elementwise and fused ops) in C++.
• Own performance and correctness with microbenchmarks and regression tests.
• Profile and optimise for the next generation of AI hardware (threading, cache locality, memory layout, kernel launch).
• Debug issues and improve quality and functionality of the product.
• Engage in Agile practices within the team and mentor colleagues.

Kenntnisse

C++

Python

Linux profiling

Teamwork

Communication

Tools

BLAS/DNN stack

PyTorch/Custom ops

Jobbeschreibung

About the job

Build the compute kernels that make next-generation AI hardware perform at its limit.

As a Senior Software Engineer, you will create high-performance AI compute libraries for Graphcore’s next-generation hardware. Your work will sit close to the hardware, where every design choice matters.

You will own kernels for linear algebra and tensor operations, including GEMM, convolutions, reductions and fused operations. You will improve performance, correctness and numerical reliability across critical AI workloads.

This role is for engineers who enjoy hard performance problems and care deeply about quality. You will help shape software that enables customers to get more from AI hardware.

The team and culture

You will join the ML Kernels and Runtime team, an expanding group focused on high-performance compute libraries. The team works close to the hardware and close to the product.

Work happens through clear ownership, practical decision-making and fast technical feedback. Engineers profile, test, debug and improve the product with accountability for real outcomes.

You will be expected to speak up, share knowledge and help others raise the bar. Mentoring, technical judgement and all-round leadership matter here

Responsibilities and Duties

• Design and implement kernels for linear algebra and tensor ops (GEMM, batched GEMM, convolutions, reductions, elementwise and fused operations) in C++
• Own performance and correctness - add microbenchmarks, regression tests, numerics validation
• Profile and optimise across for next generation of AI hardware - threading, cache locality, memory layout, and kernel launch efficiency.
• Debug issues, resolve bugs and generally improve the quality and functionality of the product
• Actively engage in and support Agile ways of working within the team
• Mentor colleagues within the team, sharing knowledge and providing guidance where appropriate

Candidate Profile

Essential

• Excellent programming and scripting skills using C++ and Python
• Understanding of processor architectures and profiling on Linux
• Possess excellent written and oral communication skills, good work ethics, high sense of teamwork
• Love to produce quality work and be a team player

Desirable

• Strong command of algorithmic performance - vectorisation, memory hierarchy, threading, lock-free patterns
• Hands-on with at least one BLAS/DNN stack and able to read/extend kernels
• Comfort with CPU micro-optimisations and numerical stability/trade-offs across FP32/FP16/BF16/FP8
• Experience integrating native code into PyTorch or similar (custom ops, extensions, dispatch keys)
• ABI/API stability and packaging for Linux system (manylinux, wheels)

Benefits

• Unlimited annual leave
• Up to 5% matched pension
• Phantom equity – share in Graphcore’s success
• True flexibility in how and where you work
• Office spaces designed for collaboration
• Free food and an on-site barista
• Health cash plan
• Income protection
• Life assurance
• Along with other benefits you can choose from (private medical insurance, dental plan etc)

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.

Join the team at Graphcore

Graphcore is one of the world’s leading innovators in Artificial Intelligencecompute. It is developing hardware, software and systems infrastructure that willunlock the next generation of AI breakthroughs and power the widespreadadoption of AI solutions across every industry.

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

Graphcore’s teams are drawn from diverse backgrounds and bring a broad rangeof skills and perspectives. A melting pot of AI research specialists, silicondesigners, software engineers and systems architects, Graphcore brings togetherdeep expertise to solve complex problems and deliver meaningful progress in AIcompute.

If you want to shape the compute libraries behind next-generation AI hardware, we’d love to hear from you.