Senior Systems Engineer, AI Gateway

Cloudflare • Austin, TX

2d • Onsite

About The Position

AI inference is becoming core infrastructure. Every serious application will need access to many models, across many providers, with reliability, observability, security, cost control, and routing built in from the start. AI Gateway is Cloudflare’s bet that this layer should exist at the network edge: close to users, close to compute, and simple enough that a developer can adopt it with one API change.
We are looking for a Senior Systems Engineer to help build that layer. This is a deeply hands-on individual contributor role for someone who can move from a half-formed product idea to a working, production-ready system quickly. You will work across the stack — from distributed systems and high-throughput APIs to developer-facing workflows, dashboards, SDKs, and docs — helping define how developers build and operate AI applications on Cloudflare.
You should be excited by the current pace of the AI ecosystem. Provider APIs change weekly, new models appear constantly, and developer expectations are rising just as quickly. AI Gateway needs engineers who can build durable infrastructure in that environment without slowing down.
We also believe AI should change how we build software, not just what we build. We dogfood AI Gateway, Workers AI, and Cloudflare’s broader agent stack heavily. You should be comfortable using AI-native tools, agents, harnesses, and automation to improve your own engineering loop — and interested in building the internal tools and context that help a small team ship like a much larger one.

Requirements

• 5+ years of experience building and operating production systems, ideally in AI infrastructure, developer platforms, cloud infrastructure, edge/proxy systems, high-scale APIs, or distributed systems.
• Strong systems engineering fundamentals: networking, APIs, reliability, observability, data modeling, performance, and operational tradeoffs.
• Experience designing or scaling distributed systems where latency, throughput, availability, and correctness all matter.
• Ability to work comfortably across the stack, from API design and product surfaces to backend services, queues, storage systems, control planes, or performance-critical code.
• Strong developer tools taste. You have used and built enough APIs, SDKs, dashboards, CLIs, docs, and internal platforms to know what makes them delightful or painful.
• Clear technical communication: you can write design docs, explain tradeoffs, review architecture, and align engineers and product partners around a practical path forward.
• A builder’s bias toward working software. You can prototype quickly, ship incrementally, and improve systems while they are already in production.
• Operational judgment. You understand that at Cloudflare scale, rare bugs are not rare for long, and you build systems that are observable, resilient, and recoverable.
• Comfort using AI-native development workflows and curiosity about how agents, tools, and automation can improve engineering productivity.

Nice To Haves

• Experience building AI/ML infrastructure, inference platforms, model gateways, LLM-powered applications, or provider abstraction layers.
• Experience building developer-facing APIs, SDKs, CLIs, dashboards, or platform products at scale.
• Hands-on experience with proxy, edge, gateway, routing, or traffic management systems.
• Familiarity with the current AI ecosystem: model providers, model capabilities, agent frameworks, inference patterns, and the rough edges developers hit in practice.
• Experience with cost controls, rate limits, caching, retries, fallbacks, evaluation, or observability for AI workloads.
• Experience with TypeScript, Go, Rust, or similar systems/backend languages.
• You have built or heavily customized your own agentic development environment: custom agents, harnesses, tools, or workflows that changed how you ship.
• You have built something with AI Gateway, Workers AI, or a competing product, and have opinions about what is missing.
• A track record of writing publicly about developer tools, infrastructure, systems, or AI products you have built.

Responsibilities

• Build core AI Gateway systems that handle high-volume inference traffic across providers, models, and Cloudflare’s global network.
• Design and implement APIs, routing primitives, observability features, controls, and developer workflows that make AI Gateway reliable and easy to adopt.
• Work across product and infrastructure boundaries with Workers AI, Agents, and the broader Developer Platform organization to make Cloudflare’s AI platform feel like one coherent product.
• Turn ambiguous product and technical ideas into prototypes, design docs, shipped features, and measurable production improvements.
• Improve reliability, performance, cost efficiency, and debuggability for latency-sensitive AI workloads.
• Build the software — and the software that builds the software: agents, tests, harnesses, evaluation loops, operational tools, and internal context that help the team move faster with confidence.
• Sweat the developer experience. Error messages, SDKs, dashboard flows, docs, examples, and API details all matter.
• Mentor other engineers through design review, code review, debugging, and technical leadership without needing people-management authority.
• Bring strong opinions, clear judgment, and a willingness to revise your view when data, users, or production reality prove otherwise.

Benefits

• Project Galileo: Since 2014, we've equipped more than 2,400 journalism and civil society organizations in 111 countries with powerful tools to defend themselves against attacks that would otherwise censor their work, technology already used by Cloudflare’s enterprise customers--at no cost.
• Athenian Project: In 2017, we created the Athenian Project to ensure that state and local governments have the highest level of protection and reliability for free, so that their constituents have access to election information and voter registration. Since the project, we've provided services to more than 425 local government election websites in 33 states.
• 1.1.1.1: We released 1.1.1.1 to help fix the foundation of the Internet by building a faster, more secure and privacy-centric public DNS resolver. This is available publicly for everyone to use - it is the first consumer-focused service Cloudflare has ever released. Here’s the deal - we don’t store client IP addresses never, ever. We will continue to abide by our privacy commitment and ensure that no user data is sold to advertisers or used to target consumers.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed