Engineering Manager, Online Serving and Inference, AI Platform
Core
Lead the development of a next-generation online serving and inference platform to enable ML practitioners to deploy large-scale AI models (LLMs, computer vision) for Netflix member ecosystems.
Role type
Senior Engineering Manager, AI/ML Infrastructure
Builds
Scalable online serving and inference platform for thousands of large-scale models
Domain
Streaming, AI/ML Infrastructure, Large Language Models
Deliverable
production ML models
Required skills
Distributed systems architecture, Kubernetes, GPU-based model inference, Foundation Model serving stacks (vLLM, Triton, TensorRT LLM, SGLang), Technical roadmap planning, Team hiring and growth
Preferred skills
Hybrid team management across time zones, Self-serve infrastructure design
Technologies
Kubernetes, vLLM, Nvidia Triton, TensorRT LLM, SGLang
Responsibilities
Partner with research and backend teams to define platform requirements; Drive architecture and build-vs-buy decisions; Build a roadmap for incremental delivery; Communicate progress to stakeholders; Maintain existing systems while developing next-gen platform; Hire and grow senior engineers
Seniority
Senior, hands-on IC leader with management responsibilities
