Elevate your career as a ML Performance Engineer with Cerebras Systems in Toronto. Leverage your Python or C++ skills to optimize the efficiency of advanced AI inference systems.

In this pivotal role within the Inference Core Platform group, you will be responsible for enhancing the performance of Cerebras' cutting-edge Wafer-Scale Engine. The team drives innovations in AI inference, enabling real-time processing and deployment. Your contributions will span from the inception of core inference capabilities to production-level performance enhancements, playing a key role in AI application development.

Key Responsibilities: • Design and implement observability systems for performance • Build scalable infrastructure for benchmarking AI tasks • Analyze and provide insights on system performance metrics • Collaborate with core teams for feature testing and validation • Develop processes for integrating high-performance features

Requirements: • Bachelor’s or Master...