ML Performance Benchmarking Engineer
Core
Design and implement end-to-end telemetry systems, build automation for performance data analysis, and optimize AI inference on the Cerebras Wafer-Scale Engine.
Role type
ML Performance Benchmarking Engineer
Builds
Inference observability systems, benchmarking infrastructure, and performance analysis tools for the Cerebras WSE.
Domain
AI hardware systems, high-performance computing, inference optimization
Deliverable
production ML models
Required skills
Python, C++, automated infrastructure scaling, throughput optimization, system behavior analysis, domain exploration
Preferred skills
Hardware-software intersection problem solving, AI workloads and architectures
Technologies
Cerebras Wafer-Scale Engine (WSE)
Responsibilities
Design telemetry systems for inference performance visibility, architect automation for performance data generation and visualization, analyze system bottlenecks to influence feature evolution, define testing methodologies for inference features.
Seniority
Mid-level, hands-on IC
