AI Research Engineer – Agentic AI

About the role

The position focuses on creating advanced agentic AI systems that can plan, reason, act, and collaborate across diverse tools and environments. It is part of Bosch's Vision and Language AI Group, which integrates large language models and 3D computer vision to build intelligent, trustworthy solutions.

Key responsibilities

• Design, build, and evaluate agentic AI systems capable of handling complex, long‑horizon tasks in single‑ and multi‑agent configurations.
• Develop robust agent harnesses and evaluation frameworks covering end‑to‑end testing, regression analysis, trace logging, replayability, and metrics for success, cost, latency, robustness, and safety.
• Implement self‑improving agent loops using reflection, critique, self‑debugging, and iterative optimization driven by execution traces and automated feedback.
• Architect and optimise agent memory architectures, including short‑term and long‑term memory, retrieval‑augmented generation, summarisation, compression, forgetting policies, and privacy‑aware mechanisms.

Required profile

Required skills

• Large language models (LLMs)
• 3D computer vision
• Retrieval‑augmented generation
• Agent memory system design