lavori da Hostess in località United States

At Bosch, we shape the future by inventing high-quality technologies and services that spark enthusiasm and enrich people’s lives. Our promise to our associates is rock-solid: we grow together, we enjoy our work, and we inspire each other. Join in and feel the difference.

The Robert Bosch GmbH is looking forward to your application!

With emerging technologies like autonomous driving and x-by-wire systems, the vehicle's onboard power supply system, known as the powernet, must meet stringent safety requirements. Failure of the powernet results in the loss of all safety-related functions such as braking, steering, and autonomous driving features. Special attention is given to batteries within the powernet due to their complex electrochemical nature. Accurate battery diagnosis is essential to predict performance, and safety validation ensures deviations are low under real-world conditions. To ensure robustness, uncertainty quantification (UQ) is necessary to assess prediction deviations. This thesis aims to develop a probabilistic surrogate model using generative AI models (e.g., Conditional Generative Adversarial Networks (cGAN), Conditional Normalizing Flows (cNF)) to quantify and distinguish different sources of uncertainty. It will also explore strategies to estimate failure probabilities with limited data while maintaining accuracy. Key research questions include how to quantify and separate epistemic and aleatory uncertainties, which generative AI models are best suited for capturing aleatory uncertainties, how to evaluate and calibrate the reliability of predicted uncertainties, the impact of data volume on uncertainty quantification accuracy, and effective failure probability estimation with small datasets.

• As part of your Master thesis, you will review state-of-the-art methodologies for uncertainty quantification (UQ) based on generative AI.
• You will prepare synthetic data for study.
• You will implement and compare different UQ models to evaluate their ability to accurately capture predictive uncertainty and distinguish between epistemic and aleatory uncertainty.
• You will improve prediction interval calibration to ensure robust and reliable uncertainty estimates.
• Finally, you will develop an approach to estimate battery diagnostic failure probability with minimal data using probabilistic surrogate models.

• Education: Master studies in any field.
• Experience and Knowledge: Background in Machine Learning, Deep Learning, Reliability or Uncertainty quantification; experience with PyTorch and deep generative models (cGANs, cNF); knowledge of battery diagnostics or systems is a plus.
• Personality and Working Practice: Self-motivated, proactive, and able to work independently.
• Languages: Very good communication skills in written and spoken German or English.

Start: According to prior agreement.
Duration: 3 - 6 months.

Requirement for this thesis is enrollment at a university. Please attach your CV, transcript of records, examination regulations, and if applicable, a valid work and residence permit.

Diversity and inclusion are integral to our culture. We welcome all applications regardless of gender, age, disability, religion, ethnicity, or sexual identity.

Need further information about the job?
Zhiyi Xu (Functional Department)
+49 711 811 92252

#LI-DNI