About the role:
We’re entering a new era of automation, where Agentic AI can automate manual work like never before. At Camunda, we’re building the operating system for this future.
Our Enterprise Agentic Automation Team (EAAT) designs and operates production-grade agentic solutions that automate critical business processes at Camunda while serving as credible proof points for our customers.
As a Senior Engineer in our Enterprise Agentic Automation Team, you will design, build, and operate enterprise-grade agentic AI systems embedded in Camunda-orchestrated workflows. You will turn AI capabilities into reliable, secure, and scalable production systems that run at the core of our organization.
What You Will Do:
Design and implement production-grade agentic orchestration systems combining executable BPMN, Camunda workers/connectors, DMN, and AI components
Design and build AI agents with clearly defined responsibilities, tools, memory strategies, and decision boundaries
Engineer and govern context pipelines (static instructions, dynamic enrichment, RAG, constraints, evaluation signals) to ensure reliable model behavior
Implement structured prompting, output enforcement, human-in-the-loop patterns, and guardrails for safe, controllable execution
Build evaluation frameworks, feedback loops, and testing for deterministic and non-deterministic systems
Operate agents in production (AgentOps): logging, monitoring, alerting, incident response, and continuous improvement
Contribute to production infrastructure standards including CI/CD, environment separation, secrets management, and security fundamentals
What You Will Bring to the Role:
Must Haves:
5+ years experience designing, building, and operating production-grade systems (backend, platform, or full-stack with strong backend depth), including scalable services, integrations, and APIs (Java/Spring or comparable)
Proven AI Engineering experience building, testing and operating LLM-powered systems in production
Hands-on experience with agent frameworks such as LangChain, LangGraph, CrewAI, or similar
Practical experience with context engineering (RAG pipelines, retrieval strategies, structured outputs, evaluation signals)
Demonstrated end-to-end ownership across design, implementation, deployment, and operations
Solid understanding of cloud-native infrastructure and production operations (CI/CD, environment separation, secrets, monitoring, incident response)
Nice to Haves:
Experience with Camunda, BPMN, DMN, or other workflow/orchestration platforms
Experience building reusable internal platforms, shared services, or developer enablement components
Experience working in a Center of Excellence or similar cross-functional transformation environment
Experience with Data Science and Machine Learning