Senior ML Systems Engineer

Job Summary

Leading the effort to optimize LLM inference performance, the full-time Senior ML Systems Engineer will measure, diagnose, and improve serving efficiency for large models in a remote environment.

Key responsibilities

• Define and build tooling for measuring inference performance metrics, ensuring rigorous and repeatable assessments
• Profile and diagnose performance issues across the serving stack, implementing solutions to enhance efficiency
• Collaborate with product and infrastructure teams to shape inference offerings and keep pace with advancements in the inference ecosystem

Required qualifications

• 5+ years of professional system engineering experience
• Hands-on experience with vLLM, SGLang, or similar serving engines in production
• Strong software engineering skills in Python, particularly in performance-critical codebases
• Solid understanding of LLM inference performance drivers, including batching and memory management
• Experience with modern inference optimization techniques and GPU profiling tools