Agent Platform Engineer

At Coframe, we’re building AI systems that can autonomously generate, verify, deploy, and personalize living interfaces at scale. As an Agent Platform Engineer, you’ll build the infrastructure, tooling, and development workflows that allow AI agents to operate safely, reliably, and at scale. Your work will support agents that generate customer interfaces, agents that contribute to Coframe’s own codebase, and automate workflows across engineering, go-to-market, and operations. Every improvement to the agent platform makes our product more capable, accelerates Coframe’s engineering velocity, and expands what teams across the company can automate. You’re a great fit if you have: A strong platform or infrastructure engineering background Strong software engineering fundamentals and experience designing scalable architectures Experience building and operating distributed systems, developer platforms, internal tooling, or compute infrastructure Experience with cloud infrastructure, serverless architectures, CI/CD, end-to-end testing, and production deployment strategies Experience deploying, scaling, profiling, and operating AI agents or LLM-based systems in production Familiarity with infrastructure for long-running execution, durable workers, isolated environments, remote browsers, and stateful workflows Strong judgment across security, reliability, performance, cost, and iteration speed A passion for engineering productivity and automating complex workflows Comfort working across infrastructure, backend systems, AI, and developer experience High ownership and the ability to operate effectively across ambiguous, fast-changing technical domains Experience building infrastructure for AI agents is a major plus What you’ll do: Build infrastructure for long-running agent execution, memory, planning, and stop-and-resume workflows Create platforms that allow AI agents to autonomously implement features, execute tests in isolated environments, analyze execution traces, and improve their own outputs Build secure, isolated execution environments that allow agents to operate safely and reliably Develop tracing, observability, evaluation, and monitoring infrastructure for autonomous AI agents Design infrastructure for durable workers, serverless compute, remote browsers, and other agent execution systems Build developer tooling that enables engineers to collaborate effectively with AI agents throughout the software development lifecycle Create internal AI platforms that allow non-engineering teams to build custom agents and automate their own workflows Improve CI/CD, testing, deployment, and developer environments Strengthen the security, reliability, and operational readiness of agent systems running in production Evaluate and implement new tooling, storage, compute, and orchestration systems Resolve production incidents with both immediate fixes and long-term improvements Create strong out-of-the-box platform defaults while supporting advanced configurations...