SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Cloudflare is building industrial-scale AI agents that power real customer interactions at global scale. This role focuses on shipping production agents on the Cloudflare edge platform, assembling Workers, Durable Objects, KV, R2, D1, Vectorize, Workers AI, AI Gateway, and the Agent SDK into customer-facing solutions.
You will own end-to-end agent development and deployment, from initial build through production support. Key responsibilities include:
- Building agents on Workers with Durable Objects for state and short-term memory management
- Wiring tools using the Agent SDK, MCP, and function calling patterns
- Leveraging Vectorize, KV, R2, and D1 for semantic memory, caching, file storage, and configuration
- Running models through Workers AI and AI Gateway, integrating third-party models as needed
- Creating evaluation frameworks, guardrails, and audit systems; measuring and tuning performance rapidly
- Building agents that summarize issues, propose fixes, and escalate cleanly to human operators
- Designing transparent dashboards and health metrics for agent monitoring
- Integrating with queues and webhooks; publishing events via Queues or Pub/Sub
- Optimizing cost per case and time to first response, backed by data
- Taking end-to-end ownership including on-call support for deployed systems
- Designing robust observability for distributed AI workflows with structured logging and end-to-end tracing across async boundaries
- Architecting security boundaries for agent-led operations, including secure credential handling, multi-layer approval gates, and fine-grained trust scoping
Cloudflare's Agent Tech team owns the complete stack for customer-facing agents running at the edge across 300+ cities worldwide. The culture emphasizes shipping fast, measuring truth, simplifying relentlessly, and owning outcomes. You'll work alongside Support, Product, Security, and AI Platform teams with visibility and leadership opportunities as one of the early engineers in the India-based AI team.
REQUIREMENTS:
- 5–10 years of professional experience
- Demonstrated success shipping production systems with public repos and releases
- Strong proficiency in TypeScript or Rust on Workers, with solid understanding of HTTP, queues, async patterns, and performance optimization
- Hands-on fluency with Durable Objects, KV or R2, and either D1 or Postgres
- Practical experience with model tooling: prompt I/O, tool calling, evaluation frameworks, and safety checks
- Observability mindset with experience implementing logs, traces, metrics, and redlines
- Experience with agent frameworks and multi-agent architectures
- Experience developing LLM evaluation frameworks, automated scoring systems, and CI-integrated quality gates
- Bias toward simple, scalable design patterns
NICE TO HAVE:
- Production experience with Workers AI, AI Gateway, and Vectorize
- Salesforce or Service Cloud experience with webhooks and case APIs
- Security depth in prompt injection protection, secrets detection, and PII handling
- Familiarity with open-source agent frameworks and ability to discern what to adopt versus build
