Tech Lead - AI and Runtime Orchestration Harness (f/m/div.)

• As part of our team, you will own the architecture of the runtime harness, connecting task planning, skill selection, and dispatch with execution state, feedback, and recovery. You define clear boundaries between AI proposals and controlled execution. • You will build AI-assisted planning and reasoning capabilities using well-defined tools and interfaces. This includes validating plans against available skills, state, and operational constraints while handling timeouts, invalid outputs, and uncertainty. • Additionally, you will integrate robot runtimes and factory systems through ROS 2 or orchestration APIs, MES/OT interfaces, PLC handshaking, and industrial event flows. You resolve state consistency, concurrency, and ordering issues. • You will design observability, replayable traces, fallback paths, and operator intervention. Working with safety and security specialists, you ensure that the harness respects plant protection and control responsibilities. • Furthermore, you will lead implementation and technical reviews while working with dedicated QA on simulation, fault injection, and plant validation. You demonstrate end-to-end reliability, latency, and recovery through reproducible evidence. • Using our Agentic AI Software Factory, you will develop implementation and verification tooling. You treat the runtime AI harness as the product being engineered, complete with its own tests, configurations, and release evidence. • Education: completed Bachelor’s or Master’s degree in Computer Science, Automation Engineering, Control Engineering or a related field • Experience and Knowledge: • hands-on experience in designing and implementing stateful AI execution systems integrated with physical or industrial environments • strong proficiency in Python/C++ or equivalent, including agent/tool orchestration, durable execution state, concurrency, and distributed failure handling • practical knowledge of action validation and recovery mechanisms, including retries, idempotency, cancellation, and recovery across external interfaces • proven ability to connect non-deterministic planning with observable, constrained execution, including integration with robot APIs or MES/OT/PLC systems • demonstrated experience with deployed systems, supported by measurable evidence on latency, reliability, and incidents • technical leadership through code and technical reviews; relevant research counts when backed by a working integrated system and rigorous evaluation • familiarity with technologies such as AI tool interfaces, planning and state machines, ROS 2, OPC UA, MQTT/Sparkplug, runtime tracing, and fault-injection testing • chatbot prototypes, prompt engineering, or high-level architecture alone are insufficient • Personality and Working Practice: you are a hands-on technical leader who builds complex systems, challenges assumptions, and connects AI capabilities with disciplined runtime engineering • Enthusiasm: making AI-assisted coordination useful and reliable in operating factories • Languages: very good spoken and written German and English https://www.bosch-ai.com   www.bosch.com/research As a global company, we are legally required to comply with applicable EU and U.S. (re-)export control and sanctions regulations. This means that for certain, particularly sensitive positions, we may only hire individuals who have undergone an additional legal screening. This position is one such sensitive role. We will therefore ask you for additional information required for this screening as the application process continues. You can find information about the processing of your data in our Privacy Notice for the application process.  Permanent, open-ended position in the engineering organization for Robert Bosch Robotics GmbH. Apply wi