Inference Core Platform Benchmarking Engineer

Cerebras Systems•Toronto, ON

53d•Hybrid

About The Position

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 Platform 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.

Requirements

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.