ML Performance Benchmarking Engineer

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. Cerebras' current customers include top model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership with Cerebras , to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference. 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. About The Role The Inference Core Platform group is at the heart of Cerebras' mission to deliver the world’s fastest AI inference. Our team builds the foundational software and hardware infrastructure that powers low-latency, high-speed, high-throughput deployment on the Cerebras Wafer-Scale Engine (WSE). We are responsible for the full stack—from model compilation and scheduling down to custom hardware kernels and driver development. The ML Performance Benchmarking team plays a pivotal role in shaping the performance and scalability of AI inference on one of the most advanced computing systems ever built. We drive the bring-up of core inference capabilities and deliver performance improvements at every stage of development – from early prototyping to production deployment. We're looking for passionate engineers to join us in redefining the limits of AI inference. If you thrive on building systems that measure, analyze, and optimize performance at scale, this is your opportunity to make a transformative impact on the future of AI. Scope of the team includes: Core Inference Observability – Design and implement end-to-end telemetry systems across the software stack, providing deep visibility into inference performance and enabling rapid iteration before and after deployment. Benchmarking Infrastructure – Architect, build, and scale the automation that generates, analyzes, and visualizes performance data used to inform business decisions across engineering and leadership. Performance Analysis – Dive deep into system behavior, dissect performance bottlenecks, and deliver actionable insights that directly influence which features ship and how they evolve. Feature Integration – Partner closely with Core Platform teams to define rigorous testing methodologies that validate inference features for peak performance. Skills & Qualifications Bachelor’s or Master’s degree in Computer Engineering, Systems Engineering, or a related field. Proficiency in Python and/or C++ programming. Proven experience in building and scaling automated infrastructure. Strong background in throughput and performance optimization techniques, especially in complex, large-scale systems. Excellent problem-solving skills and a strong analytical mindset. Demonstrated ability to dive deep into new domains. Ability to work in a fast-paced, ambiguous, and collaborative environment. Preferred Skills & Qualifications Familiarity with problem-solving at the intersection of hardware and software. Hands-on experience with AI workloads and architectures is a plus. Location On-site or hybrid at our Toronto office #LI-WA1 Why Join Cerebras People who are serious about software make their own hardware. At Cerebras we have built a breakthrough architecture that is unlocking new opportunities for the AI industry. With dozens of model releases and rapid growth, we’