PhDs on Decentralized AI for Audio-based Health Diagnostics

The Decentralized Artificial Intelligence Research Lab (DARL) at the Eindhoven University of Technology is seeking 2 talented and passionate Ph.D. candidates to join our team. These positions are part of the AiNed Fellowship project 'Private Ears, Shared Insights' funded by the NWO. Our mission is to revolutionize the field of Artificial Intelligence (AI) by developing cutting-edge collaborative learning techniques that enable AI models to learn from large-scale decentralized data while preserving user privacy. Our ultimate goal is to instill self-learning capabilities in globally distributed computational devices for everyday use.

The field of AI has seen unprecedented advancements in recent years, driven by the development of foundation models that have expanded the boundaries of machine capabilities. However, learning these models requires direct access to vast data repositories, which poses significant privacy and logistical challenges, especially in the health sensing domain that involves personal data. To address this, the DARL is at the forefront of research exploring decentralized and collaborative approaches to developing unified AI systems. Our research entails the development of novel methodologies at the intersection of self-supervised learning, data-centric machine learning, trustworthy AI, and human-machine collaboration (i.e., expert-in-the-loop) for healthcare and high-tech industries.

We are currently seeking candidates for two PhD positions, each focusing on a cutting-edge research topic within the field of audio (and speech) understanding for health monitoring:

1. Federated Audio Foundation Models:  Advance pre-training of foundation models with unlabeled private data that bring label efficiency in data-constrained environments, few-shot emerging capabilities, rapid adaptation, and synthetic data generation.

2. Domain Knowledge-Augmented Representation Learning: Development of techniques for incorporating clinical domain knowledge with physics-informed neural networks, weak supervision, active learning, and/or cross-modal knowledge transfer to improve data efficiency, generalizability, and justifiability of deep models.

These positions provide an opportunity to advance the frontier of decentralized machine learning and distributed sensing systems. Successful candidates will have the opportunity to work with a dynamic and interdisciplinary team of researchers, collaborating with experts in AI, healthcare, and industry.

Requirements:

• A master's degree (or an equivalent university degree) in Computer Science, Mathematics, Machine Learning or a related technical field.
• Strong background in deep learning with a motivation to advance fundamental techniques.
• Ability to work independently and persistently tackle difficult research problems.
• Has a solid interest in pushing the frontier of one or more of the following: a) audio and speech understanding, b) on-device learning, c) pre-training strategies, d) physics-informed neural network, healthcare, and high-tech systems.
• Excellent analytical, problem-solving, and software engineering skills with prior experience implementing machine learning algorithms using well-known frameworks (e.g., PyTorch, TensorFlow, and Flower).
• Android/iOS programming experience is a plus, or a willingness to learn these skills quickly.
• Collaborative spirit and ability to work productively as part of a multidisciplinary team.
• Strong communication skills, including proficiency in written and spoken English (C1).
• Motivated to develop your teaching skills and coach Master students.

Salary Benefits:

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:

• Full-time employment for four years, with an intermediate evaluation (go/no-go) after nine months. You will spend 10% of your employment on teaching tasks.
• Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale P (min. €2,770 max. €3,539).
• A year-end bonus of 8.3% and annual vacation pay of 8%.
• High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process.
• An excellent technical infrastructure, on-campus children's day care and sports facilities.
• An allowance for commuting, working from home and internet costs.
• A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates.

38 hours per week

De Rondom 70