Senior Software Engineer - AI Compute Libraries & Performance

<h3 class="PDq2pG_selectionAnchorContainer" data-start="135" data-end="148"><strong>About the job</strong></h3> <p data-start="150" data-end="235">Build the compute kernels that make next-generation AI hardware perform at its limit.</p> <p data-start="237" data-end="440">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.</p> <p data-start="442" data-end="665">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.</p> <p data-start="667" data-end="842">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.</p> <h3 data-start="844" data-end="864"><strong>The team and culture</strong></h3> <p data-start="866" data-end="1041">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.</p> <p data-start="1043" data-end="1229">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.</p> <p data-start="1231" data-end="1380">You will be expected to speak up, share knowledge and help others raise the bar. Mentoring, technical judgement and all-round leadership matter here</p> <h3><strong><span data-contrast="auto">Responsibilities and Duties</span></strong><span data-ccp-props="{}">&nbsp;</span></h3> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="1" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Design and implement kernels for linear algebra and tensor ops (GEMM, batched GEMM, convolutions, reductions, elementwise and fused operations) in C++</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="2" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Own performance and correctness - add microbenchmarks, regression tests,&nbsp;</span><span data-ccp-parastyle="Normal (Web)">numerics</span><span data-ccp-parastyle="Normal (Web)">&nbsp;validation</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="3" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Profile and optimise across for next generation of AI hardware - threading, cache locality, memory layout, and kernel launch efficiency.</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Debug issues, resolve bugs and&nbsp;</span><span data-ccp-parastyle="Normal (Web)">generally improve</span><span data-ccp-parastyle="Normal (Web)">&nbsp;the quality and functionality of the product</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="5" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Actively engage in and support Agile ways of working within the team</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="6" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Mentor colleagues within the team, sharing knowledge and providing guidance where appropriate</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <p><strong><span data-contrast="none">Candidate Profile&nbsp;</span></strong>&nbsp;<br><span data-ccp-props="{}">&nbsp;</span></p> <p><strong><span data-contrast="auto">Essential</span></strong><span data-ccp-props="{}">&nbsp;</span></p> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="1" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Excellent programming and scripting skills using C++ and Python</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="2" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Understanding of processor architectures and profiling on Linux</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="3" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Possess excellent written and oral communication skills,&nbsp;</span><span data-ccp-parastyle="Normal (Web)">good work</span><span data-ccp-parastyle="Normal (Web)">&nbsp;ethics, high sense of&nbsp;</span><span data-ccp-parastyle="Normal (Web)">team-work</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> <li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Love to produce quality work and be a team player</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <p><strong><span data-contrast="auto">Desirable</span></strong><span data-ccp-props="{}">&nbsp;</span></p> <ul> <li data-leveltext="" data-font="Symbol" data-listid="21" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="1" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Strong command of algorithmic performance - vectorisation, memory hierarchy, threading, lock-free patterns</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="21" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="2" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Hands-on with at least one BLAS/DNN stack and able to read/extend kernels</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="21" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="3" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Comfort with CPU micro-optimisations and numerical stability/trade-offs across FP32/FP16/BF16/FP8</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <ul> <li data-leveltext="" data-font="Symbol" data-listid="21" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Experience integrating native code into&nbsp;</span><span data-ccp-parastyle="Normal (Web)">PyTorch</span><span data-ccp-parastyle="Normal (Web)">&nbsp;or similar (custom ops, extensions, dispatch keys)</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> <li data-leveltext="" data-font="Symbol" data-listid="21" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;469769226&quot;:&quot;Symbol&quot;,&quot;469769242&quot;:[8226],&quot;469777803&quot;:&quot;left&quot;,&quot;469777804&quot;:&quot;&quot;,&quot;469777815&quot;:&quot;multilevel&quot;}" data-aria-posinset="5" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">ABI/API stability and packaging for Linux system (</span><span data-ccp-parastyle="Normal (Web)">manylinux</span><span data-ccp-parastyle="Normal (Web)">, wheels)</span></span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335559738&quot;:0,&quot;335559739&quot;:0}">&nbsp;</span></li> </ul> <h3 class="p1">Benefits</h3> <p class="p1">· Unlimited annual leave<br>· Up to 5% matched pension<br>· Phantom equity – share in Graphcore’s success<br>· True flexibility in how and where you work<br>· Office spaces designed for collaboration<br>· Free food and an on-site barista<br>· Health cash plan<br>· Income protection<br>· Life assurance<br>· Along with other benefits you can choose from (private medical insurance, dental plan etc)</p> <p class="p1">We welcome people from all backgrounds and experiences and are committed to building an inclusive environment where everyone can do their best work.</p> <p class="p1">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.</p> <h3 class="p1">Join the team at Graphcore</h3> <p class="p1">Graphcore is one of the world’s leading innovators in Artificial Intelligence&nbsp;compute. It is developing hardware, software and systems infrastructure that will&nbsp;unlock the next generation of AI breakthroughs and power the widespread&nbsp;adoption of AI solutions across every industry.</p> <p class="p1">As part of the SoftBank Group, Graphcore is a member of an elite family of&nbsp;companies responsible for some of the world’s most transformative technologies.&nbsp;Together, they share a bold vision: to enable Artificial Super Intelligence and&nbsp;ensure its benefits are accessible to everyone.</p> <p class="p1">Graphcore’s teams are drawn from diverse backgrounds and bring a broad range&nbsp;of skills and perspectives. A melting pot of AI research specialists, silicon&nbsp;designers, software engineers and systems architects, Graphcore brings together&nbsp;deep expertise to solve complex problems and deliver meaningful progress in AI&nbsp;compute.</p> <p class="p1">If you want to shape the compute libraries behind next-generation AI hardware, we’d love to hear from you. Apply now to help build what comes next.</p>

Find more English Speaking Jobs in United Kingdom on Arbeitnow