AI Research Engineer – Agentic AI

The Bosch Research and Technology Center North America with offices in Sunnyvale, California, Pittsburgh, Pennsylvania, and Cambridge, Massachusetts is a part of the global Bosch Group (www.bosch.com), a company with over 70 billion euro revenue, 400,000 employees worldwide, a very diverse product portfolio, and a history spanning over 125 years. The Research and Technology Center North America (RTC-NA) is dedicated to providing technologies and system solutions for various Bosch business fields, primarily in the field of artificial intelligence, energy technologies, internet technologies, circuit design, semiconductors and wireless, as well as advanced MEMS design.

As part of the global research organization, our AI research in Silicon Valley focuses on Foundation Models and Gen AI, Human-AI Collaboration and Trustworthy AI, AI for Advanced Driver-Assistance Systems (ADAS) and Autonomous Systems, AI Systems Engineering, and Industry AI. We develop scalable, intelligent, and trustworthy AI solutions to enable inspiring user experiences for Bosch products and services in application areas such as ADAS, smart manufacturing, enterprise AI, healthcare, smart home, and building solutions.

Originating from Bosch AI research in Silicon Valley, our Vision and Language AI Group advances cutting-edge research in two core AI areas: large language models (LLMs) and 3D computer vision. In the LLM space, we focus on AI agents, retrieval-augmented generation, and effective adaptation of LLMs to Bosch domain-specific applications. In 3D vision, we advance spatial intelligence with 3D world models that perceive, reconstruct, and simulate the physical world, enabling reliable embodied control and sim-to-real transfer. By integrating these two areas, we aim to build intelligent systems that can perceive, reason, and communicate seamlessly across both language and spatial environments. We also actively collaborate with leading groups in academia and industry to promote research ideas and publish research findings in internationally renowned conferences and journals such as ACL, EMNLP, CVPR, ICCV, ECCV, NeurIPS, AAAI and CoRL.

Responsibilities

Design, build, and evaluate agentic AI systems that can plan, reason, act, and collaborate across tools and environments, including single- and multi-agent setups for complex, long-horizon tasks.; 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 strategies driven by agent experience, execution traces, and automated feedback.; Architect and optimize agent memory systems, including short-term and long-term memory, retrieval-augmented generation, summarization, compression, forgetting policies, and privacy-aware retention.; Enable reliable deployment of agents on constrained and edge environments, focusing on model/runtime optimization, partial or offline execution, secure tool-use, and seamless edge-cloud coordination.

Requirements

Bachelor or master's degree in computer science or engineering; Strong software engineering skills in Python; Hands-on experience with LLMs and agentic systems, such as tool-using agents, planner-executor patterns, multistep reasoning pipelines, RAG systems; Solid understanding of ML fundamentals and practical model usage, including prompting, evaluation, and error analysis; Ability to design experiments and interpret results, including ablations, statistical thinking, clear success criteria and measurable KPIs; Strong communication and documentation skills including clear write-ups, reproducible experiments, and crisp technical presentations

Nice to have

3+ years experiences in industrial research.; Experience with one or more of the following topics:; Agent frameworks; Structured generation; Agent memory management; Self-improving agents; LLM fine-tuning & reinforcement learning; Model optimization for edge; Harness engineering; Hands-on experience on production of AI systems