Arbeitszeit & Home-Office

  • Teilzeit
  • Vollzeit
  • Home-Office

Anzeigenart

Anzeigenalter

11 Treffer für "deep learning" Jobs

Sortierung:    -  
Erhalten Sie alle neuen Stellenangebote per E-Mail.

PhD in AI & Data Science for Cancer Research with Real World Impact (m/f/d)

Deutsches Krebsforschungszentrum (DKFZ)
Home-Office
Vollzeit
Digital prevention, diagnostics and therapy guidance A 20-member team from the fields of medicine, molecular biology and informatics/data science is at the forefront of machine learning for cancer prevention and diagnosis. We are currently working on bringing an AI-powered medical device to market that assists dermatologists in diagnosing melanoma - one of the most dangerous forms of skin cancer while also innovating novel approaches of personalized skin cancer prevention. Help shape the future of personalized skin cancer prevention and diagnostics by developing AI-driven methods that integrate diverse biomedical datasets. We seek real world impact, meaning the PhD project is in collaboration with two large German companies (Beiersdorf and HEINE Optotechnik), to help patients benefit from the developed solutions as fast as possible. As part of this PhD position, you will not only contribute to cutting-edge AI research in dermatology but also lead a key bioinformatics project aimed at integrating multiple data sources for personalized skin cancer prevention. Your work will be instrumental in building a scalable bioinformatic infrastructure that connects epigenetic data, microbiome analyses, and AI-enhanced dermatoscopic imaging. Development of AI-driven models for skin cancer diagnostics and early detection, with a focus on robustness, explainability, and clinical applicability. Building a bioinformatic pipeline that integrates epigenetic profiling (TapeLift), microbiome data, and AI-based image analysis to create predictive models for personalized prevention strategies. Designing and validating a digital dashboard for real-time risk stratification and clinical decision-making, ensuring accessibility for both clinicians and patients. Collaborating with interdisciplinary experts , including dermatologists, AI researchers, statisticians, and computational biologists, to optimize data-driven prevention strategies. Validating the developed models and infrastructure through pilot studies with data from 100 study participants, ensuring real-world applicability. Publishing in top-tier scientific journals and contributing to clinical studies to validate the effectiveness of AI-assisted diagnostics.
Heidelberg
15.04.2025

Thesis - Self-supervised Learning for Battery Health Estimation f/m/d

AVL List GmbH
We are looking for a motivated student to conduct their master thesis in the area of Li-ion batterie modelling using state-of-the-art machine learning modelling techniques. This master thesis focuses on developing advanced techniques to estimate the health estimation of battery health and performance in the automotive industry. By leveraging deep neural network architectures for learning the trajectory of the degradation with existing amount of test data, the aim is to estimate the state-of-health without having the entire history of the battery's operation (zero-shot learning). The thesis will contribute to the overcome practical issues for SOH estimation in-field and will offer valuable insights into understanding the influencing aging factors. Literature research: Identify the state-of-art for the specific applications and rank most relevant architectures/techniques Data preparation and pre-processing: Utilize time series analysis and aggregation techniques to create a pipeline for feature engineering during charge cycles. Selection of the target variables Data segmentation: Prepare sample of data from existing experimental datasets for training the models Comparison and ablation study: Establish a set of baseline methods (i.e., MLP, RNN, LSTM) that will be used for comparison purposes Final model evaluation: Utilize the trained models for final evaluation in both experimental and real-world data Sensitivity analysis: Utilize Explainable-AI methods to pinpoint influencing factors and explain model's outputs
Graz
11.04.2025
Erhalten Sie alle neuen Stellenangebote per E-Mail.