<div class="content-intro"><p><strong data-stringify-type="bold">Why work at Nebius<br></strong>Nebius is leading a new era in cloud computing to serve the global AI economy. We create the tools and resources our customers need to solve real-world challenges and transform industries, without massive infrastructure costs or the need to build large in-house AI/ML teams. Our employees work at the cutting edge of AI cloud infrastructure alongside some of the most experienced and innovative leaders and engineers in the field.</p><p><strong>Where we work<br></strong>Headquartered in Amsterdam and listed on Nasdaq, Nebius has a global footprint with R&D hubs across Europe, North America, and Israel. The team of over 800 employees includes more than 400 highly skilled engineers with deep expertise across hardware and software engineering, as well as an in-house AI R&D team.</p></div><p><span data-contrast="auto"><span data-ccp-charstyle="Strong"><strong>About the role:</strong></span></span></p><p><span data-contrast="auto"><span data-ccp-charstyle="Strong">Token Factory is a part of Nebius Cloud, one of the world’s largest GPU clouds, running tens of thousands of GPUs. We are building an inference platform that makes every kind of foundation model — text, vision, audio, and emerging multimodal architectures — fast, reliable, and effortless to deploy at massive scale.</span></span></p><p> </p><p><strong><span data-contrast="auto"><span data-ccp-charstyle="Strong">Responsibilities:</span></span></strong></p><ul><li data-leveltext="" data-font="Symbol" data-listid="4" 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="auto"><span data-ccp-parastyle="Normal (Web)">Develop and </span><span data-ccp-parastyle="Normal (Web)">optimize</span><span data-ccp-parastyle="Normal (Web)"> low-level kernels and runtime components for AI inference</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="4" 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="auto"><span data-ccp-parastyle="Normal (Web)">Improve performance of inference engines GPU platforms</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="4" 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="auto"><span data-ccp-parastyle="Normal (Web)">Profile and debug system-level and hardware-level performance issues</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="4" 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="auto"><span data-ccp-parastyle="Normal (Web)">Integrate support for new hardware architectures (Hopper, Blackwell</span><span data-ccp-parastyle="Normal (Web)">,</span></span><span data-contrast="auto"><span data-ccp-parastyle="Normal (Web)"> Rubin</span></span><span data-contrast="auto"><span data-ccp-parastyle="Normal (Web)">)</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="4" 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="auto"><span data-ccp-parastyle="Normal (Web)">Collaborate with </span><span data-ccp-parastyle="Normal (Web)">ML </span><span data-ccp-parastyle="Normal (Web)">and </span><span data-ccp-parastyle="Normal (Web)">backend</span> <span data-ccp-parastyle="Normal (Web)">teams to </span><span data-ccp-parastyle="Normal (Web)">optimize</span><span data-ccp-parastyle="Normal (Web)"> end-to-end execution</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><p> </p><p><strong><span data-contrast="auto"><span data-ccp-charstyle="Strong">Required Qualifications:</span></span></strong></p><ul><li data-leveltext="" data-font="Symbol" data-listid="5" 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="auto"><span data-ccp-parastyle="Normal (Web)">Strong </span><span data-ccp-parastyle="Normal (Web)">proficiency</span><span data-ccp-parastyle="Normal (Web)"> in C++</span><span data-ccp-parastyle="Normal (Web)">,</span><span data-ccp-parastyle="Normal (Web)"> OR </span><span data-ccp-parastyle="Normal (Web)">expertise</span><span data-ccp-parastyle="Normal (Web)"> in GPU programming with a focus on low-level high-performance coding and memory management</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="5" 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="auto"><span data-ccp-parastyle="Normal (Web)">Experience in </span><span data-ccp-parastyle="Normal (Web)">GPU programming or </span><span data-ccp-parastyle="Normal (Web)">systems-level software development</span><span data-ccp-parastyle="Normal (Web)">, </span><span data-ccp-parastyle="Normal (Web)">e.g.</span><span data-ccp-parastyle="Normal (Web)"> operating system internals, kernel modules, or device drivers</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="5" 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="auto"><span data-ccp-parastyle="Normal (Web)">Hands-on experience </span><span data-ccp-parastyle="Normal (Web)">with </span><span data-ccp-parastyle="Normal (Web)">profiling and debugging tools to </span><span data-ccp-parastyle="Normal (Web)">identify</span><span data-ccp-parastyle="Normal (Web)"> performance issues on both CPUs and GPUs, and the ability to optimize code based on those findings.</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="5" 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="auto"><span data-ccp-parastyle="Normal (Web)">Solid understanding of CPU/GPU architecture and memory hierarchy</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><p> </p><p><strong><span data-contrast="auto"><span data-ccp-charstyle="Strong">Preferred Qualifications:</span></span></strong><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></p><ul><li data-leveltext="" data-font="Symbol" data-listid="6" 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="auto"><span data-ccp-parastyle="Normal (Web)">Experience with GPU</span><span data-ccp-parastyle="Normal (Web)"> computing</span><span data-ccp-parastyle="Normal (Web)"> programming</span><span data-ccp-parastyle="Normal (Web)">:</span><span data-ccp-parastyle="Normal (Web)"> CUDA, </span><span data-ccp-parastyle="Normal (Web)">ROCm</span><span data-ccp-parastyle="Normal (Web)">, </span><span data-ccp-parastyle="Normal (Web)">CUTLASS, Cute, </span><span data-ccp-parastyle="Normal (Web)">ThunderKittens</span><span data-ccp-parastyle="Normal (Web)">, </span><span data-ccp-parastyle="Normal (Web)">Triton, Pallas, Mosaic GPU</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="6" 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="auto"><span data-ccp-parastyle="Normal (Web)">Familiarity with ML inference runtimes (e.g. </span><span data-ccp-parastyle="Normal (Web)">TensorRT</span><span data-ccp-parastyle="Normal (Web)">, TVM)</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="6" 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="auto"><span data-ccp-parastyle="Normal (Web)">Knowledge of Linux internals, drivers, or compiler toolchains</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="6" 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="auto"><span data-ccp-parastyle="Normal (Web)">Experience with tools like perf, </span><span data-ccp-parastyle="Normal (Web)">VTune</span><span data-ccp-parastyle="Normal (Web)">, Nsight, or </span><span data-ccp-parastyle="Normal (Web)">ROCm</span><span data-ccp-parastyle="Normal (Web)"> profiler</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><ul><li data-leveltext="" data-font="Symbol" data-listid="6" 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="auto"><span data-ccp-parastyle="Normal (Web)">Familiarity with popular inference engines (e.g. such as </span><span data-ccp-parastyle="Normal (Web)">vLLM</span><span data-ccp-parastyle="Normal (Web)">, </span><span data-ccp-parastyle="Normal (Web)">sglang</span><span data-ccp-parastyle="Normal (Web)">, TGI)</span></span><span data-ccp-props="{"134233117":true,"134233118":true}"> </span></li></ul><p> </p><p><span data-ccp-props="{}"><em data-stringify-type="italic">We conduct coding interviews as part of the process.</em></span></p><div class="content-conclusion"><p><strong>What we offer</strong> </p><ul><li>Competitive salary and comprehensive benefits package.</li><li>Opportunities for professional growth within Nebius.</li><li>Flexible working arrangements.</li><li>A dynamic and collaborative work environment that values initiative and innovation.</li></ul><p><span data-contrast="auto">We’re growing and expanding our products every day. If you’re up to the challenge and are excited about AI and ML as much as we are, join us!</span></p></div>