Summary

The staff machine learning engineer will optimize production LLM and VLM inference across model compression, serving engines, and GPU performance. The role focuses on building benchmarking and deployment workflows for Nebius's AI cloud platform.

Responsibilities

• Own platform-level inference optimization pillars
• Build reusable evaluation and benchmarking frameworks
• Deploy and extend production inference engines
• Productionize model compression and quantization workflows
• Diagnose bottlenecks across runtime and cluster layers
• Provide technical direction on shared performance goals