A technology company specializing in AI collaborates with large European organizations to integrate AI into operational systems where work actually happens. The company builds software that allows AI systems to perform real work within businesses.
This involves connecting agents to ERP systems, internal APIs, documents, databases, and business applications; giving them carefully controlled access to tools; evaluating their behavior; placing humans in the right places; and getting the resulting system into production.
What you do
- Work directly with customer teams to map real workflows, identify where AI can create value, and turn ambiguous problems into buildable solutions.
- Rapidly prototype and develop AI agents, integrations, workflows, and supporting software using LLMs, APIs, enterprise data, and existing systems.
- Integrate what you build into the customer's real environment — ERP, CRM, SaaS, APIs, databases, identity, and internal tooling.
- Work alongside customer engineering teams to get systems into production, monitor them in the real world, and iterate based on actual usage.
What they ask Strong hands-on experience with:
- Python and modern software engineering, including APIs, databases, Git, testing, and CI/CD.
- LLM and agentic systems, including tool calling, RAG, structured outputs, orchestration, and evaluation.
- Production AI, including observability, guardrails, human-in-the-loop workflows, and reliability.
- Cloud and infrastructure, ideally Azure, AWS, or GCP, with Docker/Kubernetes experience.
- Enterprise integrations, including REST APIs, authentication/SSO, and systems such as SAP, ServiceNow, Salesforce, or Microsoft 365.
Experience with frameworks such as LangGraph, LangChain, LlamaIndex, MCP, Langfuse, or LangSmith is useful, but the focus is more on what you have actually shipped than which tools you have used.
How to apply
View the full assignment text and application details once your tailored application is ready.
Order a tailored application to view the full assignment and application details.
More context, less searching.
You get enough context to judge whether this job is relevant. The full brief, client details and next steps stay available inside the app.