Back to all jobs
- Seniority
- Staff
About the role
<p><strong>Salary Range: PLN 350,700 - 474,400 PLN<br></strong></p>
<p><strong>Subject to alignment to the responsibilities and duties of the role</strong></p>
<p> </p>
<h2><strong>About Graphcore </strong></h2>
<p>At Graphcore, we’re building the future of AI compute.</p>
<p>We’re a team of semiconductor, software and AI experts, with deep experience in creating the complete AI compute stack - from silicon and software to infrastructure at datacenter scale.</p>
<p>As part of the SoftBank Group, backed by significant long-term investment, we are delivering key technology into the fast-growing SoftBank AI ecosystem.</p>
<p>To meet the vast and exciting AI opportunity, Graphcore is expanding its teams around the world.</p>
<p>We are bringing together the brightest minds to solve the toughest problems, in a place where everyone has the opportunity to make an impact on the company, our products and the future of artificial intelligence.</p>
<p> </p>
<p><strong><span data-contrast="none">Job Summary</span></strong><strong><span data-contrast="none"> </span></strong><span data-ccp-props="{}"> </span></p>
<p><span data-contrast="none">As a </span><span data-contrast="auto">Staff Software Engineer,</span><span data-contrast="none"> </span><span data-contrast="none">you will be responsible for development of new and support existing kernels for liner algebra operations on a new generation of AI hardware.</span><span data-ccp-props="{}"> </span></p>
<p><span data-ccp-props="{}"> </span></p>
<p><strong><span data-contrast="auto">The Team</span></strong><span data-ccp-props="{}"> </span></p>
<p><span data-contrast="none">This is an exciting opportunity to join an expanding team at Graphcore. The ML Kernels & Runtime team is responsible for delivering high performance compute library to help customers gain the maximum performance from AI hardware.</span><span data-ccp-props="{}"> </span></p>
<p><span data-ccp-props="{}"> </span></p>
<p><strong><span data-contrast="auto">Responsibilities and Duties</span></strong><span data-ccp-props="{}"> </span></p>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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, </span><span data-ccp-parastyle="Normal (Web)">numerics</span><span data-ccp-parastyle="Normal (Web)"> validation</span></span><span data-ccp-props="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Debug issues, resolve bugs and </span><span data-ccp-parastyle="Normal (Web)">generally improve</span><span data-ccp-parastyle="Normal (Web)"> the quality and functionality of the product</span></span><span data-ccp-props="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<p><span data-ccp-props="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></p>
<p><strong><span data-contrast="none">Candidate Profile </span></strong> <br><span data-ccp-props="{}"> </span></p>
<p><strong><span data-contrast="auto">Essential</span></strong><span data-ccp-props="{}"> </span></p>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="13" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="13" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="13" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="3" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Experience testing numerical/performance-sensitive code</span></span><span data-ccp-props="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="13" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Hands-on with reproducibility/determinism, tolerance design, and benchmarking</span></span><span data-ccp-props="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="13" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="5" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Possess excellent written and oral communication skills, </span><span data-ccp-parastyle="Normal (Web)">good work</span><span data-ccp-parastyle="Normal (Web)"> ethics, high sense of </span><span data-ccp-parastyle="Normal (Web)">team-work</span></span><span data-ccp-props="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="13" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="6" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<p><span data-ccp-props="{"134233117":false,"134233118":false,"335559685":720,"335559738":0,"335559739":0}"> </span></p>
<p><strong><span data-contrast="auto">Desirable</span></strong><span data-ccp-props="{}"> </span></p>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="17" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="17" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="17" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" 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="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="17" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">Experience integrating native code into </span><span data-ccp-parastyle="Normal (Web)">PyTorch</span><span data-ccp-parastyle="Normal (Web)"> or similar (custom ops, extensions, dispatch keys)</span></span><span data-ccp-props="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="17" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="5" data-aria-level="1"><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">ABI/API stability and packaging </span><span data-ccp-parastyle="Normal (Web)">on Linux </span><span data-ccp-parastyle="Normal (Web)">system (</span><span data-ccp-parastyle="Normal (Web)">manylinux</span><span data-ccp-parastyle="Normal (Web)">, wheels)</span></span><span data-ccp-props="{"134233117":false,"134233118":false,"335559738":0,"335559739":0}"> </span></li>
</ul>
<p> </p>
<h2><strong>Benefits</strong></h2>
<p>In addition to a competitive salary, Graphcore offers annual leave policy, medical and dental health plans, a gym card, and employee pension (matched up to 4%). We review our benefits on a yearly basis to ensure we offer a valuable and rewarding benefits programme to our employees. We welcome people of different backgrounds and experiences; we’re committed to building an inclusive work environment that makes Graphcore a great home for everyone. We offer an equal opportunity process and understand that there are visible and invisible differences in all of us. We can provide a flexible approach to interview and encourage you to chat to us if you require any reasonable adjustments.</p>
<p><span data-ccp-props="{}"> </span></p>
731,000+ hidden jobs like this
Graphcore and thousands of companies post here first — often days before LinkedIn or Indeed. Your first 5 applications are free; go Pro to apply without limits.
Everything Pro unlocks:
- Unlimited applications — free stops at 5
- Track every application in one place
- Apply straight to the source, one click
- Save & organize roles you love
- Roles pulled from company boards before the big sites
