Staff Software Engineer, Inference Cloud

<div class="content-intro"><p><span data-contrast="none">Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. Our novel wafer-scale architecture provides the AI compute power of dozens of GPUs on a single chip, with the programming simplicity of a single device. This approach allows Cerebras to deliver industry-leading training and inference speeds and empowers machine learning users to effortlessly run large-scale ML applications, without the hassle of managing hundreds of GPUs or TPUs.&nbsp;</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;201341983&quot;:0,&quot;335559685&quot;:0,&quot;335559737&quot;:240,&quot;335559738&quot;:240,&quot;335559739&quot;:240,&quot;335559740&quot;:279}">&nbsp;</span></p> <p>Cerebras' current customers include top model labs, global enterprises, and cutting-edge AI-native startups.&nbsp;<a href="https://openai.com/index/cerebras-partnership/&quot;&gt;OpenAI recently announced a multi-year partnership with Cerebras</a>, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference.&nbsp;</p> <p>Thanks to the groundbreaking wafer-scale architecture, Cerebras Inference offers the fastest Generative AI inference solution in the world, over 10 times faster than GPU-based hyperscale cloud inference services. This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation.</p></div><p><span data-contrast="auto">Location: Sunnyvale</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&quot;335559738&quot;:240,&quot;335559739&quot;:240}">&nbsp;</span></p> <p><span data-contrast="auto">We're&nbsp;hiring&nbsp;a&nbsp;Staff&nbsp;Engineer to own major areas of the architecture of our Inference Cloud Platform. This team owns the cloud layer behind our Inference Service, with responsibility for availability, latency, reliability, and global scale.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&quot;335559738&quot;:240,&quot;335559739&quot;:240}">&nbsp;</span></p> <p><span data-contrast="auto">This is a hands on IC role for an engineer who wants to work on the hardest distributed systems problems in the stack: multi-region traffic architecture, graceful degradation under bursty AI workloads, performance at high QPS, and the operating model for a platform that has to stay fast and available under load.&nbsp;You'll&nbsp;write code, lead key architectural decisions in your domain, debug production issues, and help shape technical direction across adjacent teams.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&quot;335559738&quot;:240,&quot;335559739&quot;:240}">&nbsp;</span></p> <p><span data-contrast="auto">If&nbsp;you're&nbsp;interested in building the next-generation architecture of a globally distributed inference platform,&nbsp;we'd&nbsp;like to&nbsp;talk.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&quot;335559738&quot;:240,&quot;335559739&quot;:240}">&nbsp;</span></p> <p><strong><span data-contrast="auto">Responsibilities</span></strong><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&quot;335559738&quot;:240,&quot;335559739&quot;:240}">&nbsp;</span></p> <ul> <li data-leveltext="" data-font="Symbol" data-listid="3" data-list-defn-props="{&quot;335552541&quot;:1,&quot;335559683&quot;:0,&quot;335559684&quot;:-2,&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;hybridMultilevel&quot;}" data-aria-posinset="1" data-aria-level="1"><strong><span data-contrast="auto">Platform Direction.</span></strong><span data-contrast="auto">&nbsp;Help shape the technical direction for the Inference Cloud Platform, including multi-region topology, failure domains, service boundaries, and system evolution over time, and&nbsp;own&nbsp;the roadmap for major technical areas.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&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;335559683&quot;:0,&quot;335559684&quot;:-2,&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;hybridMultilevel&quot;}" data-aria-posinset="2" data-aria-level="1"><strong><span data-contrast="auto">Core Cloud Systems.</span></strong><span data-contrast="auto">&nbsp;Design and build critical platform components such as service discovery, request routing, load balancing, caching, batching, and traffic management for AI inference workloads.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&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;335559683&quot;:0,&quot;335559684&quot;:-2,&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;hybridMultilevel&quot;}" data-aria-posinset="3" data-aria-level="1"><strong><span data-contrast="auto">Reliability &amp; Performance.</span></strong><span data-contrast="auto">&nbsp;Architect active-active systems with rapid failover, graceful degradation, and clear SLOs. Drive system-level improvements in latency, throughput, capacity efficiency, and resilience under unpredictable demand.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&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;335559683&quot;:0,&quot;335559684&quot;:-2,&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;hybridMultilevel&quot;}" data-aria-posinset="4" data-aria-level="1"><strong><span data-contrast="auto">Traffic Control &amp; Service Tiers.</span></strong><span data-contrast="auto">&nbsp;Define platform mechanisms for admission control, quota management, rate limiting, and differentiated quality of service across workload types and customer tiers.</span><span data-ccp-props="{&quot;134233117&quot;:false,&quot;134233118&quot;:false,&quot;335551550&quot;:0,&quot;335551620&quot;:0,&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;335559683&quot;:0,&quot;335559684&quot;:-2,&quot;335559685&quot;:720,&quot;335559991&quot;:360,&quot;46976922