Software Engineer, AI Agents
Cloudflare · In-Office
About this role
**Software Engineer, AI Agents** **About Cloudflare** At Cloudflare, we’re on a mission to help build a better Internet. We protect and accelerate Internet applications online—without adding hardware, installing software, or changing a line of code. Our intelligent global network gets smarter with every request, improving performance while decreasing spam and other attacks. **Why This Role Matters** 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. **Role Intent** Ship production agents on the Cloudflare stack. Build, deploy, learn, repeat. Your code is the front door for Cloudflare customers. **Location & Experience** - **Location:** India, Bangalore - **Experience:** 5–10 years **What You Will Do** - 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, and 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) - Build robust observability for distributed AI workflows (structured logging + end-to-end tracing across async boundaries) - Architect security boundaries for agent-led operations (secure credential handling, multi-layer approval gates, fine-grained trust scoping for mutative actions) **Must Have** - Demonstrated success shipping production systems (repos/releases showing 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 model tooling: prompt I/O, tool calling, evals, safety checks - Observability mindset: logs, traces, metrics, redlines - Experience with **a2a/multi-agent frameworks** - Experience building LLM evaluation frameworks (automated scoring systems, CI-integrated quality gates) - Bias for simple, scalable designs **Nice to Have** - Production experience with **Workers AI**, **AI Gateway**, and **Vectorize** - **Salesforce** / **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 **How We Build** - Align fast on what matters - Divide and conquer—own your piece - Ship and watch customers use it - Learn and repeat **Interview Signal** Expect to demonstrate your ability to: - Build a mini agent on Workers using the Agent SDK - Store session memory in Durable Objects - Add semantic recall with Vectorize - Ship behind a KV flag with traces and observability - Push to production fast and take ownership **Team Mission** 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, Vect
Listing freshness
CronJobs last confirmed this listing 15h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.