Staff / Principal Machine Learning Engineer, Serving - USA

📋 Description

• Build and optimize real-time ML serving systems.
• Containerize models and deploy to production.
• Profile and optimize latency and throughput on GPUs.
• Collaborate with research to ship reliable APIs.
• Lead end-to-end deployment from research to prod.
• Maintain reliability and performance as core features.

🎯 Requirements

• Inference optimization: vLLM, TRT-LLM
• Model acceleration: quantization, distillation, caching, batching
• High-performance systems: C++, CUDA, Rust, Python
• Distributed systems: Kubernetes, Ray, multi-GPU/multi-node
• Public work: open-source contributions to inference engines
• Background: PhD in CS, Physics, Math, or equivalent

🎁 Benefits

• Relocation assistance
• Mountain View office
• Bonus and equity
• Benefits package
• Flat, collaborative culture with fast iterations