About this role
About the Role
Build and operate the backend systems that help AI agents turn user requests into reliable work across connected services. You will own core infrastructure spanning API integrations, execution environments, and multi-tenant data, with a direct impact on system reliability and user outcomes.
What You'll Do
- Design and operate a tool gateway that exposes connected APIs and MCP integrations through a composable Python SDK, including routing, authentication, rate limits, and reliability features.
- Run persistent, isolated Linux sandboxes for workspaces, with a focus on security, autoscaling, and cost efficiency.
- Build and maintain durable, high-performance data systems for multi-tenant state and persistence.
- Identify integration failures, resolve them, and improve system architecture to prevent recurring issues.
- Work closely with company leadership on technical decisions and deliver improvements at a fast pace.
- Engage with users and contribute directly to shipped backend work.
What We're Looking For
- Experience building and operating production backend systems, including distributed systems designed for scale and reliability.
- Hands-on expertise with sandboxing and OS-level isolation, including containers, Linux internals, and safely running untrusted code.
- Experience building Python services and comfort using Modal for infrastructure.
- Experience integrating third-party APIs, including OAuth, webhooks, and rate limits.
- Experience designing multi-tenant systems, with attention to durability, cost, and failure isolation.
- A background in infrastructure, platform, developer tools, reliability engineering, or code execution systems.
Compensation & Benefits
Visa sponsorship is not available.
Location
On-site in Munich, Germany.