Senior Systems Engineer, Workers AI
Core
Design and build core infrastructure for real-time AI inference (voice, LLMs, customer models) across Cloudflare's global network using heterogeneous GPU fleets.
Role type
Senior Systems Engineer (AI Infrastructure)
Builds
Serverless inference platform, model deployment platform, and high-performance computing infrastructure for edge AI.
Domain
Cloud infrastructure, High-Performance Computing (HPC), Distributed Systems, AI/ML Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Distributed systems engineering, Rust (asynchronous), Networking protocols (TCP, HTTP, WebSocket), Performance optimization, Load balancing, Caching strategies
Preferred skills
Container orchestration (Kubernetes, Nomad), Large-scale inference serving architecture
Technologies
Rust, Kubernetes, Nomad, TCP, HTTP, WebSocket
Responsibilities
Develop and maintain serverless inference platform components for high availability and scalability; Optimize model scheduling and request routing logic to reduce latency; Drive improvements in platform reliability and resilience; Expand observability stack (metrics, logging, tracing); Lead cross-functional technical projects from concept to deployment; Mentor junior engineers.
Seniority
Senior, hands-on IC with technical leadership
