Software Engineer Agentic AI (Coding Agent Harness)
- Hiring from
- Switzerland
- Work type
- Hybrid
- Posted
625,072 remote jobs, straight from company career pages
100% free · New jobs every minute
Show job descriptionHide job description
Do you already spend more time on prompts, skills and evals than on boilerplate code? Do you want to build the coding agent that Swiss Post developers work with every day, and shape what it knows, what it may do and how it gets better? Then you might be exactly who we're looking for. Swiss Post IT is changing how software gets built: AI agents take over a growing part of the work, while people set the intent, review and steer. Our developers already use coding agents today. With you, we turn that into a Swiss Post coding agent an enterprise can rely on.
How you make a difference
-
You specify, build, test and ship our coding agent, pre-configured with skills, prompt templates, rules and plugins.
-
In addition, you curate the baseline configuration and our library of skills, so that teams get a version they can trust: reviewed, versioned and easy to roll back.
-
You write evals for skills, prompts and agent workflows, so that every change shows whether it makes the agent better or just different.
-
At the same time you build guardrails into the agent itself, such as permissions, sandboxing and hooks, so that the safe way is also the easy way.
-
You connect our internal systems via MCP and evaluate new large language models against the work our developers actually do.
-
Moreover, you work with the pilot teams and the growing number of engineers who use the agent every day, and turn what you learn into better skills and defaults.
What you have to offer
-
You have several years of hands-on software engineering experience, for example in Python, TypeScript, Go or Java, including APIs and CI/CD pipelines such as GitHub Actions.
-
In addition, you have practical experience building with LLMs and coding agents beyond the chat window: skills, prompts, tools, MCP servers or agent workflows that others actually use.
-
You have experience applying GenAI tools pragmatically in real software engineering work, with a clear understanding of where they help and where engineering judgment is still required.
-
Moreover, you bring a security mindset for agents, including secrets, dependencies, permissions, input and output controls and data protection.
-
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 bring a strong engineering foundation and have built something real with 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. Help us transform our company into the "Swiss Post of tomorrow"!
