Software Development Engineer, Senior II AI Agent (m/f/d)

In this role you will own the architecture and implementation of AI agent and multi-agent systems for real products, driving reliable, scalable, and measurable AI-enabled software. You will shape end-to-end design decisions and integrate agentics into existing platforms, delivering production-grade code and robust quality strategies. You will collaborate across disciplines to translate requirements into robust AI-powered software and continuously improve development processes. The opportunity offers meaningful impact on complex systems and a chance to contribute to BorgWarner’s mission of a cleaner, energy-efficient world.

• Driving Change – innovative technology and personal responsibility
• Flexible working arrangements (mobile working)
• gym subsidy
• canteen allowance
• free beverages
• competitive compensation and development opportunities

• Own architecture and implementation of AI agent and multi-agent systems for complex landscapes
• Lead end-to-end technical design decisions for agentic solutions, from requirements to integration
• Develop production-ready code and models using modern languages/frameworks
• Advance software architecture for scalability, performance, maintainability, and clean integration patterns
• Define and maintain evaluation strategies for agentic systems (offline evaluations, regression suites)
• Support project execution with effort estimation, progress tracking, and escalation
• Improve development processes with automation and efficiency
• Create and communicate technical documentation and results to support transparency

• Master’s degree in computer science, software engineering or a comparable technical field (or equivalent qualification)
• Several years of hands-on software development in complex environments
• Strong proficiency in at least one OO language (Python, Java, C++ or comparable)
• Practical experience with AI agent systems or multi-agent workflows, including LLMs, prompting, embeddings, and tool/function calling
• Experience with evaluation frameworks for LLM/agent systems (offline evaluations, regression suites, red-teaming, reliability metrics)
• Experience with observability and tracing for LLM apps and debugging multi-step tool workflows
• Solid understanding of software architecture, distributed systems, and integration patterns
• Proven ability to ensure software quality with testing strategies and analysis of failures
• Strong analytical/problem-solving skills and ability to develop robust solutions
• Excellent communication and collaboration in interdisciplinary, international teams
• Experience in technical mentoring or guidance

• excellent communication
• team collaboration across disciplines
• mentoring or technical guidance
• AI agent systems and multi-agent workflows
• LLMs, prompting, embeddings, tool/function calling
• evaluation frameworks for AI/LLM systems