ML Performance Engineer at Cerebras Systems

Transform AI inference with Cerebras Systems as an ML Performance Benchmarking Engineer. Leverage Python and C++ skills to optimize high-speed system performance and scalability.

The Cerebras Inference Core Platform group is in search of an ML Performance Benchmarking Engineer to lead advancements in AI inference processes. The successful candidate will work on core telemetry systems, build benchmarking infrastructure, and analyze performance r expertise in throughput optimization will contribute to delivering actionable insights that influence product features.

Key Responsibilities:

• Design end-to-end telemetry systems for inference

• Build and scale benchmarking infrastructure for performance data

• Analyze system behavior to identify performance bottlenecks

• Collaborate with Core Platform teams for rigorous testing

• Optimize automated infrastructure for AI workloads

Requirements:

• Bachelor’s or Master’s in Computer Engineering or Related Field

• Proficiency in Python and/or C++ programming

• Experience in scaling automated infrastructure

• Strong problem-solving and analytical skills

• Familiarity with hardware-software optimization

Make a significant impact on AI performance and innovation at Cerebras Systems.
#J-18808-Ljbffr