AI Engineer, Agent Infrastructure

Zed•San Francisco, CA

About The Position

Zed is building the first AI-native, licensed neobank in the Philippines designed to democratize access to premium financial services for young professionals in global markets. The current banking system is broken, often shutting out the world’s youngest and fastest-growing consumer classes—we’re here to fix it. Our team is uniquely positioned to solve this. We are Stanford engineers and former YC founders who have spent our careers at the intersection of banking and hyper-growth startups like Square, Facebook, and Box. We’ve been here before, having previously built and exited Symple (YC W'17), a fast-growing B2B payments company. We are backed by world-class investors, including Accel, Valar, Immad Akhund (Mercury), Dalton Caldwell (Y Combinator), and Kunal Shah (Cred). The Role We're hiring an engineer to own the infrastructure layer behind our production AI agents. This is not a prompt engineering role. It's not a UI role. It's about the harness around LLMs — the systems that determine how agents actually execute tasks, interact with tools, access internal and external systems, stay within permission boundaries, and behave reliably in production. You'll sit at the intersection of backend infrastructure and product, and what you build will define how AI is deployed across the company.

Requirements

Direct experience shipping production LLM or agent systems end-to-end — orchestration, evaluation, reliability, not just prototypes
Strong backend or infrastructure engineering foundation (distributed systems, APIs, platform engineering)
Experience with workflow orchestration, automation systems, or agent frameworks
Familiarity with evaluation and observability loops for AI systems
Ability to think across both infrastructure concerns and product behavior — this role requires both

Nice To Haves

You've built agent systems that take real actions, not just generate text
You've designed execution environments — task runners, sandboxes, job systems
You've worked on AI that's deeply embedded in a real product, not a side project or internal tool
You have experience with observability and evaluation loops for AI systems in production

Responsibilities

Build and own the execution layer for AI agents — task orchestration, tool calling, state management
Define how agents interact with internal systems and external APIs
Design sandboxed environments and permissioning models for safe, controlled agent execution
Build evaluation, monitoring, and debugging infrastructure for agent behavior in production
Integrate agents into real product workflows where correctness and reliability are non-negotiable
Improve system performance across latency, cost, and quality tradeoffs