Software Engineer, AI Agents

Cloudflare • San Francisco, CA

18h • Onsite

About The Position

At Cloudflare, we're building industrial-scale AI agents that support customers directly. This isn't research theater. Your code will power real customer interactions from day one, at global scale. Cloudflare already has the parts. You will assemble Workers, Durable Objects, KV, R2, D1, Vectorize, Workers AI, AI Gateway, and the Agent SDK into real agents customers use every day. The Agent Tech team owns the end to end stack for customer facing agents on Cloudflare. Everything runs at the edge. Core Stack: Workers, Durable Objects, KV, R2, D1, Queues, Pub/Sub, Vectorize, Workers AI, AI Gateway, Pages, Zero Trust. Principles: Ship fast. Measure truth. Simplify relentlessly. Own outcomes.

Requirements

• Demonstrated success shipping production systems. Repos and releases that show real work.
• Strong in TypeScript or Rust on Workers. HTTP, queues, async, performance
• Fluency with Durable Objects, KV or R2, and either D1 or Postgres
• Hands on with model tooling. Prompt I/O, tool calling, evals, safety checks
• Observability mindset. Logs, traces, metrics, redlines
• Experience with a2a/multi-agent frameworks
• Experience developing LLM evaluation frameworks; automated scoring systems, CI-integrated quality gates.
• Bias for simple, scalable designs

Nice To Haves

• Workers AI, AI Gateway, and Vectorize in production
• Salesforce or Service Cloud experience.
• Webhooks and case APIs
• Security depth. Prompt injection protection, secrets detection, PII handling
• OSS agent frameworks. Know what to borrow and what to throw away.

Responsibilities

• Build agents on Workers with Durable Objects for state and short term memory
• Wire tools with the Agent SDK, MCP, and function calling
• Use Vectorize, KV, R2, and D1 for semantic memory, cache, files, and config
• Run models through Workers AI and AI Gateway; integrate third parties when needed
• Create evals, guardrails, and audits. Measure, tune, re-ship fast
• Build agents that summarize, propose fixes, and escalate cleanly to humans
• Expose agent health and metrics in transparent dashboards. No mystery boxes
• Integrate with queues and webhooks; publish events on Queues or Pub/Sub
• Cut cost per case and time to first response. Prove it with data.
• Take end to end ownership including on call for what you ship (with team support)
• Design and maintain robust observability for distributed AI workflows, implementing structured logging and end-to-end tracing across async service boundaries to ensure visibility into agent reasoning and execution.
• Architect security boundaries for agent-led operations; implementing secure credential handling, multi-layer approval gates, and fine-grained trust scoping for mutative actions.

Benefits

• Visibility, leadership opportunities, and a direct hand in shaping Cloudflare's AI roadmap.
• Autonomy, accountability, and trust.
• Knowledge sharing, mentorship, and continuous learning.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: No Education Listed
• Number of Employees: 501-1,000 employees