Principal Software Engineer

Job Summary

A company is looking for a Principal Software Engineer - AI Inference.

Key Responsibilities

• Drive upstream-first engineering in vLLM/SGLang, including authoring PRs and engaging in development discussions
• Build and implement features to improve inference-runtime efficiency, latency, and tail behavior
• Optimize core hot paths across the stack and improve multi-GPU and multi-node inference

Required Qualifications

• 15+ years of experience in building production software with a focus on systems engineering
• Expertise in LLM inference/serving systems and production performance tradeoffs
• Strong programming skills in Rust, C++, Python, and CUDA
• Experience with GPU performance analysis tools and methodologies
• BS/MS in Computer Science, Computer Engineering, or a related field (or equivalent experience)