Software Engineer Agentic AI (Agent Platform)

When you think of AI agents, do you think more of identities, permissions, and telemetry than of demos? Do you want to build the platform that enables the developers at Schweizerischen Post to work with AI agents securely, traceably, and at a reasonable price? Then you might be exactly the right person for us. The IT of Schweizerischen Post AG is changing the way software is developed: AI agents are taking over a growing part of the work, while humans define the goals, verify the results, and control the processes. Together with you, we are building an enterprise-grade platform for AI agents and scaling it from pilot teams to our DevOps organization.

What you can achieve

• You create the platform on which our AI agents run, from the agent runtime environment as well as AI and MCP gateways to identity and access management for humans and agents. Where the Post already has suitable building blocks, you integrate them instead of developing parallel solutions.
• Furthermore, you implement guardrails, guidelines, and governance rules in code and enforce them centrally - from data protection to the access rights of the agents.
• You set up cost controls, quotas, and alerts so that usage remains transparent and budgets are maintained.
• In addition, you define and automate metrics, baselines, and telemetry so that we can show what changes in delivery by the agents, and not just how often they are used.
• You provide proven Large Language Models and connect the platform to our existing SDLC tools.
• You also ensure that the platform operates reliably and verifiably, so that we can trace which agent did what on whose behalf.

What you bring with you

• You have several years of practical experience in software or platform development, for example with Go, Python, Java, or TypeScript, and bring solid experience with Infrastructure as Code as well as CI/CD pipelines such as GitHub Actions.
• You also have experience with APIs, identity and access management (OAuth/OIDC), as well as container or cloud platforms such as Kubernetes or AWS.
• You have a strong understanding of security for platforms on which AI agents run, including secret management, permissions, network access, input and output controls, and data protection.
• Furthermore, you understand how AI agents work technically - from model APIs via tool calls to MCP - and therefore know which requirements a corresponding platform must fulfill.
• You have experience in the pragmatic use of GenAI tools in practical software development. Knowledge in areas such as AI and MCP gateways, prompt firewalls, Policy as Code, FinOps, OpenTelemetry, Backstage, and DORA metrics is an advantage but can also be acquired with us.
• You have very good oral and written English skills. Knowledge of a national language is an advantage.

You do not have to meet every single criterion. If you have built and operated platforms that others rely on and are truly interested in AI agents, we would be happy to hear from you. It is more important to us how you think and how you learn than whether your profile perfectly matches all the keywords in the job description.