Advanced Technology: Compiler Engineer
VerifiedAbout the Role
<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. </span><span data-ccp-props="{"134233117":false,"134233118":false,"201341983":0,"335559685":0,"335559737":240,"335559738":240,"335559739":240,"335559740":279}"> </span></p> <p>Cerebras' current customers include top model labs, global enterprises, and cutting-edge AI-native startups. <a href="https://openai.com/index/cerebras-partnership/">OpenAI recently announced a multi-year partnership with Cerebras</a>, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference. </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><h3><strong><span data-contrast="none"><span data-ccp-parastyle="heading 3">About The Team</span></span></strong><span data-ccp-props="{"134245418":true,"134245529":true,"201341983":0,"335559738":281,"335559739":281,"335559740":240}"> </span></h3> <p>Cerebras builds wafer-scale AI processors—single chips delivering tens of PB/s of memory bandwidth and a dataflow architecture that accelerates at a granularity no multi-device system can match. <span data-contrast="auto"><span data-ccp-parastyle="Normal (Web)"><span data-teams="true"><span id="message-body-1775506131882" class="fui-ChatMessage__body r7802u9 ___1be7vh5 f10pi13n ftqa4ok f2hkw1w f8hki3x f1d2448m f1bjia2o ffh67wi f1j6vpng f1pniga2 f987i1v f1ffjurs f15bsgw9 f14e48fq f18yb2kv fd6o370 ffwy5si f3znvyf f57olzd f4stah7 f480a47 fs1por5 fk6fouc figsok6 fkhj508 f19n0e5 f9ijwd5 f14diw67 f1o0qvyv f9ggezi f1xp5gbu f150uoa4 fd9xhir fxugw4r fo7qwa0 fxowb0n f11ghf3q f13aoclr flypziy f10kwr27 fquw1qa fftr39l f13lathq f15hsm81 f2ss68y ffb60jq f8nuap2 f13nk4fk f7jacry fq08z5q fd9af6s fr74w9q fcl9uv6 f13sm7pj f1u6qqly f16wpxbl faim3u9 f6cs3qo fa2w2z3 fd39nx6 f10gn8j9 frcqmxy f1w9ws4k f1ddxkqj fd10euv fvuz61 f1nbc6gw"><span id="content-1775506131882" class="fui-Primitive _11tzqds f1oy3dpc f89hs3r fqtknz5 fyvcxda"></span></span></span>The Advanced Technology Group (ATG) is </span><span data-ccp-parastyle="Normal (Web)">Cerebras</span><span data-ccp-parastyle="Normal (Web)">’ pathfinding organization. We</span></span> <span data-contrast="auto"><span data-ccp-parastyle="Normal (Web)">work ahead of product to explore new architectures, </span><span data-ccp-parastyle="Normal (Web)">demonstrate</span><span data-ccp-parastyle="Normal (Web)"> breakthrough performance on</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">scientific and AI workloads, and shape the technical roadmap for future Cerebras hardware and</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">software. Our work regularly appears at top-tier venues (Supercomputing, SIAM, IEEE, and</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">NeurIPS</span><span data-ccp-parastyle="Normal (Web)">) and directly influences the design of next-generation wafer-scale systems.</span></span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559739":0,"335559740":240}"> </span></p> <h3><strong><span data-contrast="none"><span data-ccp-parastyle="heading 3">About The Role</span></span></strong><span data-ccp-props="{"134245418":true,"134245529":true,"201341983":0,"335559738":281,"335559739":281,"335559740":240}"> </span></h3> <p><span data-contrast="auto"><span data-ccp-parastyle="Normal (Web)">We are seeking Compiler Engineers to </span><span data-ccp-parastyle="Normal (Web)">join </span><span data-ccp-parastyle="Normal (Web)">a small team</span></span><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)"> of specialists</span><span data-ccp-parastyle="Normal (Web)"> working on</span><span data-ccp-parastyle="Normal (Web)"> our emerging Tungsten language compiler.</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">Tungsten is Cerebras’ dataflow programming language, purpose-built for wafer-scale hardware.</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">You will work on the Tungsten compiler from language design through code generation, building</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">the toolchain that translates high-level intent into efficient execution across hundreds of</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">thousands of cores with a memory and interconnect model unlike anything in conventional </span></span><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">computing.</span></span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559739":0,"335559740":240}"> </span></p> <p><span data-contrast="none"><span data-ccp-parastyle="Normal (Web)">This is not incremental work on an existing backend. The architecture is new, the</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">programming model is new, and the compiler is where those two things meet. You will</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">collaborate closely with Cerebras’ ASIC, kernel, and AI teams, and your design decisions will</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">directly shape both the language and the hardware it targets. Beyond the compiler itself, the</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">broader toolchain—runtime, debugger, simulator—is still being built, and we are equally</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">interested in engineers who want to own those pieces of the</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">developer</span><span data-ccp-parastyle="Normal (Web)"> experience on novel</span><span data-ccp-parastyle="Normal (Web)"> </span><span data-ccp-parastyle="Normal (Web)">hardware.</span></span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559739":0,"335559740":240}"> </span></p> <h3><strong>What You Will Do </strong></h3> <ul> <li><span data-contrast="none">Design and implement compiler passes across the Tungsten toolchain: mid-end</span> <span data-contrast="none">optimization, backend code generation, instruction scheduling, register allocation,</span> <span data-contrast="none">assembler, and linker.</span><sp
Related Searches
Explore more opportunities matching this role's title, location, and skills.
Ready to apply?
Click below to apply directly on Cerebras Systems's careers page.
Similar Roles
Staff Software Engineer, Kubernetes Platform
Tech Lead, Android Core Product - Berlin, Germany
Software Engineer, Platform - Munich, Germany
Get the top 10 hyper-growth roles delivered to your inbox every Tuesday.