Research Engineer- Advanced Driver Assistance Systems (ADAS) Job at Robert Bosch Sp. z o.o. (Sunnyvale)

Job Description

As a Research Engineer for ADAS AI Systems, you contribute to research projects at the forefront of the ADAS/AD industry.

Perform engineering tasks to support research in core AI and machine learning fields to enable Embodied AI (including computer vision, autonomous planning, open-world learning, and so on) for related business domains of ADAS/AD, industrial automation, robotics etc. These tasks include the development and training of AI-planners (using imitation and reinforcement learning), data-preparation tasks (auto-labeling, filtering, etc.), integrating models into a system context, setting up evaluation and benchmarking pipelines, creating demonstrations and visualizations and more
Support the team in pushing the boundaries in (modular) end-to-end perception and planning for ADAS/AD, and large vision-language-(action) models
Collaborate with a global team to transfer cutting-edge research findings to Bosch's operational units
Implement research results to solve real-world challenges, ensuring high-quality system integration within Bosch's existing platforms
Stay abreast of the latest technological advancements and market trends by attending academic conferences, technical events, and seminars
Document and disseminate research findings through high-caliber publications and/or patent submissions

Master’s degree in computer science, robotics or a related discipline or undergraduate degree with at least 2 years of industry experience after graduation
A minimum of 2 years of R&D experience, or an equivalent graduate research background, primarily in AI technologies including Computer Vision and Robotic or Automotive Motion and Behavioral Planning
Proficiency in one or more programming languages commonly used in machine learning (e.g., Python, C++, Rust)
Strong software engineering competencies
Strong interpersonal, communication, and teamwork capabilities
Knowledge of major machine learning frameworks like TensorFlow or PyTorch
Hands-on experience in reinforcement learning for behavior or motion planning or other applicable contexts and familiarity with common RL techniques (e.g. PPO, DQN, DDPG)

1 year industry experience in relevant fields after graduation
Experience with real-world product development and deployment of autonomous systems
Hands-on experience building, training and applying multimodal transformer-based sequence-to-sequence models, especially multimodal vision-language-action models
Hands-on experience in computer vision and deep learning, with work in any of the following areas: multimodal transformers, multimodal language models, diffusion models, NeRF, gaussian splatting, object detection / segmentation, 3D scene understanding, sensor calibration, SfM, voxel/BEV grid-based feature representation