Software Engineer Agentic AI (Agent Platform)
Die Schweizerische Post
- Location
- Onsite (Bellinzona, TI · Bern, BE · Lausanne, VD · Neuchâtel, NE)
- Compensation
- CHF 133k - CHF 148k/yr
- Employment
- Part-time
- Level
- Mid Level
About the role
Swiss Post IT is seeking a Software Engineer to build and maintain an enterprise-ready platform for AI agents. The role focuses on integrating existing building blocks, enforcing governance and security, and automating telemetry to ensure agent reliability and cost transparency.
Skills
Full job details
Do you think about AI agents in terms of identities, permissions and telemetry rather than demos? Do you want to build the platform that lets Swiss Post developers work with agents safely, traceably and at a cost we can explain? Then you might be exactly who we're looking for. Swiss Post IT is changing how software gets built, with AI agents taking over a growing part of the work while people set the intent, review and steer. With you, we build an enterprise-ready platform for AI agents and scale it from pilot teams across our DevOps organization.
How you make a difference
- You build the platform our agents run on, from agent runtime and AI and MCP gateways to identity and access for people and agents. Where Swiss Post already has a building block, you integrate it rather than build a second one.
- In addition, you turn guardrails, policies and governance rules into code and enforce them centrally, from data protection to what agents are allowed to reach.
- You set up cost controls, quotas and alerts, so that usage stays transparent and budgets hold.
- Moreover, you define and automate metrics, baselines and telemetry, so that we can show what agents change in delivery, not just how often they are used.
- You provision approved large language models and connect the platform to our existing SDLC tools
- In addition, you keep the platform reliable and auditable, so that we can trace which agent did what, on whose behalf.
What you have to offer
- You have several years of hands-on software or platform engineering experience, for example in Go, Python, Java or TypeScript, and solid experience with infrastructure as code and CI/CD pipelines such as GitHub Actions.
- In addition, you have experience with APIs, identity and access (OAuth/OIDC) and container or cloud platforms such as Kubernetes or AWS.
- You bring a security mindset for platforms that run agents, including secrets, permissions, network access, input and output controls and data protection.
- Moreover, you understand how agents work under the hood, from model APIs to tool calls and MCP, enough to know what a platform for them has to handle.
- You have experience applying GenAI tools pragmatically in real software engineering work, while nice-to-have topics such as AI and MCP gateways, prompt firewalls, policy as code, FinOps, OpenTelemetry, Backstage and DORA metrics are things you can also learn with us.
- You have a very good spoken and written command of English and Knowledge of another national language is a plus.
You don't need to tick every box. If you have built and run platforms that others rely on and take a real interest in AI agents, we'd like to hear from you. We care more about how you think and how you learn than about a perfect keyword match.