Graduate Software Engineer, AI Compute Libraries & Performance 2027

<p><strong>Location:</strong> Bristol, UK <br><strong>Start date: </strong>September 2027<br><strong>Application deadline</strong>: Midnight, 29th November 2026 <br><em>We encourage you to apply early, as we may close applications before the advertised deadline.</em></p> <h3>The Graduate Programme at Graphcore</h3> <p>Join Graphcore in a permanent role and start your career with two years of hands-on learning. From day one, you’ll be trusted to take ownership, share your ideas and help shape what we’re creating. You’ll tackle challenging problems alongside a team who support your development and are as excited about your success as you are.</p> <p><iframe style="display: table; margin-left: auto; margin-right: auto;" src="https://www.youtube.com/embed/sUqy-WuXPsE" width="560" height="314"></iframe></p> <h3>What you’ll work on</h3> <p><span data-contrast="none">Use your programming skills and curiosity to help AI models run efficiently on next-generation Graphcore hardware.</span><span data-ccp-props="{"201341983":0,"335559738":240,"335559739":240,"335559740":240}"> </span></p> <p><span data-contrast="none">In AI Compute Libraries & Performance, you’ll contribute to C++ libraries and compute kernels for machine learning workloads. Your work will include:</span><span data-ccp-props="{"201341983":0,"335559738":240,"335559739":240,"335559740":240}"> </span></p> <ul> <li><strong><span data-contrast="none">Developing compute kernels:</span></strong><span data-contrast="none"> Implement and improve operations such as matrix multiplication (GEMM), convolutions, reductions, elementwise operations and fused kernels that combine multiple operations.</span><span data-ccp-props="{"201341983":0,"335559738":240,"335559739":240,"335559740":240}"> </span></li> <li><strong><span data-contrast="none">Understanding and improving performance:</span></strong><span data-contrast="none"> Use profiling and microbenchmarks to measure execution speed and investigate how threading, cache locality, memory layout and kernel launch efficiency affect performance.</span><span data-ccp-props="{"201341983":0,"335559738":240,"335559739":240,"335559740":240}"> </span></li> <li><strong><span data-contrast="none">Checking correctness and reliability:</span></strong><span data-contrast="none"> Build regression tests and numerical checks, investigate issues and improve the quality of the libraries our customers use.</span><span data-ccp-props="{"201341983":0,"335559738":240,"335559739":240,"335559740":240}"> </span></li> </ul> <p><span data-contrast="none">Through these projects, you’ll develop practical experience connecting numerical computing with how code runs on hardware, helping deliver software that is fast, accurate and reliable.</span><span data-ccp-props="{"201341983":0,"335559738":240,"335559739":240,"335559740":240}"> </span></p> <h3><span data-contrast="none">Your team and support</span><span data-ccp-props="{"201341983":0,"335559739":0,"335559740":240}"> </span></h3> <p><span data-contrast="none">You’ll join a team building high-performance compute libraries that help customers get more from Graphcore hardware. Our work brings together machine learning, numerical computing and accelerator performance, with colleagues sharing their expertise to solve engineering problems.</span><span data-ccp-props="{"201341983":0,"335559738":240,"335559739":240,"335559740":240}"> </span></p> <p><span data-contrast="none">You’ll contribute to clearly scoped projects and build your skills with guidance from engineers working in performance and low-level software. Togethe