AI Engineer – Agentic AI Platform

About the role

Hero is building a group-wide AI Centre of Competence to turn artificial intelligence into a managed portfolio of value-generating solutions. As AI Engineer, you will design the shared foundation on which Hero's AI use cases run, from the Agentic AI Platform and governed access layer to the knowledge base and observability capabilities. The position is based in Lenzburg, Switzerland, with a hybrid setup of at least 3 days onsite.

Key responsibilities

• Design, build and evolve the Agentic AI Platform, covering agent orchestration, tool use, retrieval-augmented generation, prompt and agent management and model selection, moving solutions from proof of concept to production with CI/CD and LLMOps.
• Create the MCP Gateway as the governed entry point to enterprise data and tools, integrating with systems such as SAP S/4HANA, Microsoft 365 and SharePoint.
• Build the AI Knowledge Base on Azure, with ingestion pipelines, chunking, embeddings, hybrid retrieval and permission-aware filtering, connected to Snowflake data.
• Set up an observability layer tracking agent and model quality, latency, failures, costs, usage and guardrail events, supporting compliance with the EU AI Act, GDPR, nFADP and an ISO 42001-based AI management system.
• Partner with the AI Use Case Manager and business owners to develop proofs of concept and MVPs.

Required profile

• Degree in computer science, software engineering, applied mathematics or a related field.
• At least five years of software engineering experience, including a minimum of two years building GenAI or LLM applications in production.
• Hands-on experience with agentic frameworks and the Model Context Protocol, and understanding of reusable platforms combining agent orchestration, RAG, tool use, model selection, evaluation and prompt engineering.

Required skills

• Python; TypeScript or C# is an advantage.
• Azure AI Foundry, AI Search, API Management, ADLS Gen2 and Entra ID; AWS Bedrock is a plus.
• Snowflake, SQL and dbt, with knowledge of semantic layers and knowledge graphs.
• Docker, Kubernetes, infrastructure as code and CI/CD via GitHub Actions or Azure DevOps.

What we offer

• Flexible working hours and 40% home office.
• Excellent social benefits and a modern working environment.
• Free snacks and drinks, subsidized meals and free parking.