PhD and postdoc positions (speculative application)
I expect to have openings for PhD and postdoc positions within the next few months.
Drop me an email if you are passionate about doing impactful fundamental research on one or more of the following topics:
- Graph machine learning (GML)
- Neural algorithmic reasoning (NAR)
- Theory of neural networks with a focus on structured problems, generalization and inductive bias (NNs)
I am mostly interested in applicants that combine practical experience with deep learning, knowledge of algorithms and an affinity for CS theory.
Your application should include: (1) a motivation letter explaining some of the problems that you are excited about and why you want to work with me, (2) your CV, (3) as well as the names and addresses of 2-3 people you have worked with and are willing to provide a reference letter. Postdoc applicants should also attach three selected publications.
Relevant works per topic:
- What graph neural networks cannot learn (GML)
- Erdos goes neural (NAR)
- What training reveals about neural network complexity (NNs)
Post-doc researcher: machine learning for protein design (now closed)
We are hiring a postdoc to work on the interface between AI and computational protein design. The project will be carried out at EPFL in collaboration with Bruno Correia, Michael Bronstein, Pierre Vandergheynst, and the Swiss Data Science Center.
We offer a 2-year position in EPFL, a vibrant university located in one of the most beautiful countries. The salary is very attractive.
The researcher will partake in an interdisciplinary effort to design novel proteins using tools from deep learning. Relevant work from our team: https://tinyurl.com/1stzxmkj
Candidate’s profile. The ideal candidate combines
- practical deep learning know-how (mainly pytorch),
- past publications on top machine learning venues (e.g., ICML, NeurIPS, ICLR, CVPR, …)
- Knowledge of biology is not required–but a willingness to learn is.
The following are considered a plus:
- experience with generative models and/or reinforcement learning.
- experience with invariant and equivariant models (graph neural networks, neural networks for sets, …)
We are also open to applications from computational biologists with good knowledge of python and deep learning.
To apply. If you are interested, send me by email:
- a motivation letter explaining how your expertise fits the current position,
- your CV,
- the names and addresses of three references,
- three selected publications.