Senior AI Inference Systems Engineer

CloudFlare; San Francisco (CA); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Cloudflare is seeking a Senior Systems Engineer for its AI inference platform. You will design and build core infrastructure powering AI inference across a global network, working with AI/ML engineers, hardware partners, and product teams to solve distributed systems challenges.

Hybrid roles in Austin, TX or London, UK with exposure to edge compute and real-time workloads. The ideal candidate has deep Rust experience, proficiency in network protocols, and a track record of optimizing performance

Qualifications

• Proven experience in systems engineering, with a focus on distributed, high-performance systems.
• Expert proficiency in Rust programming, particularly in an asynchronous environment.
• Deep understanding of networking protocols (TCP, HTTP, WebSocket).
• Solid experience with scaling and performance optimization techniques, including load balancing and caching.

Responsibilities

• Platform Architecture: Develop and maintain core components of the serverless inference platform to ensure high availability and scalability.
• Optimization & Performance: Improve model scheduling to increase efficiency and reduce latency.
• System Reliability: Improve platform reliability and resilience by mitigating systemic risks.
• Observability: Expand the observability stack with metrics, logging, tracing and alerts.

Skills

Rust

Distributed systems

Networking

Performance tuning

Tools

Kubernetes

Nomad

Job description

Cloudflare is seeking a Senior Systems Engineer for its AI inference platform. You will design and build core infrastructure powering AI inference across a global network, working with AI/ML engineers, hardware partners, and product teams to solve distributed systems challenges.

Hybrid roles in Austin, TX or London, UK with exposure to edge compute and real-time workloads. The ideal candidate has deep Rust experience, proficiency in network protocols, and a track record of optimizing performance