Agentic Software Engineer

About the role

Zühlke is building its AI Factory, a production line for software in which AI agents turn an approved requirement into a verified change, with people setting targets, agents doing the work and people assuring the result. As an Agentic Software Engineer you join the core team that builds this system, takes it into client projects and pushes it to production, designing the agents, the workflows that connect them and the quality gates that check their output.

Key responsibilities

• Design and build multi-agent workflows with clear hand-offs, durable state and explicit failure handling.
• Build agent loops that refine, plan, implement and review until an independent evaluator lets the result pass, defining stop conditions, retry budgets and which model runs which step.
• Engineer the context agents work with: tools and knowledge access over code, documentation and domain via MCP.
• Build agent harnesses: instruction files, skills, custom agents, hooks and CI checks, with rules in tests and hooks rather than prompts.
• Implement spec-driven development with traceability from requirement to code and test.
• Build quality gates that run deterministic checks first, then evals and AI judgement, ending with a human decision backed by evidence.
• Harden agents against prompt injection and run them in isolated sandboxes with least-privilege access.
• Make agent behaviour observable and auditable, with an audit trail of decisions, cost per task and lead-time metrics.
• Work with client teams to deploy agents and harnesses, and own the value after go-live.

Required profile

• At least seven years of professional software engineering, with a track record of owning code quality in production systems.
• Has built a working agentic system and will demo it during selection.
• Hands-on experience with agent orchestration, including multi-agent workflows, state and failure handling.
• Experience with evals as quality gates, guardrails against prompt injection and tracing agent runs.
• Working knowledge of responsible AI and AI governance, such as EU AI Act obligations.
• Experience taking software to production with clients and staying accountable for its value; delivery in regulated industries is a strong plus.
• Team player who communicates technical trade-offs to non-engineers and speaks English confidently.

Required skills

• Strong programming in Python or TypeScript; Java or .NET is a plus.
• Agent frameworks such as Claude Agent SDK, Azure AI Foundry or LangGraph.
• Context engineering and the Model Context Protocol (MCP).
• CI/CD and Git practice; GitLab, containers and Kubernetes are a plus.