PhD Position in Mechanistic Interpretability

We are looking for a PhD candidate to work on mechanistic interpretability of ML models. You will conduct your work at the University of Amsterdam, where you will be a part of the Institute for Logic, Language, and Computation and the Informatics Institute.

As machine learning (ML) models continue to have influence on everyday life, it becomes increasingly important to understand how they work internally. Mechanistic interpretability is an emerging subfield of ML where the task is to reverse engineer how modern deep learning architectures make predictions. In this PhD position, you will focus on developing and evaluating post-hoc interpretability techniques, meaning that we are trying to understand predictions from ML models that have already been trained.

What are you going to do?
As a PhD candidate, you will conduct independent research on mechanistic interpretability. This is a relatively new field, so there is substantial room to contribute. This can be done for various types of AI models (e.g., transformers, GNNs, etc), and/or in the context of various applications, ranging from social network analysis to molecular simulation; as long as the data contains ground truth explanations, we can evaluate the new methods we propose.

We are looking for an enthusiastic and creative individual who is interested in the following:

• Developing novel techniques for understanding how information flows through deep neural networks.
• Developing evaluation frameworks for assessing the correctness of mechanistic interpretability techniques.
• Connecting empirical findings about model behavior to theoretical frameworks about computation.
• Contributing to making AI systems more interpretable, reliable, and safe.
• Publishing and presenting your findings at international AI conferences such as NeurIPS, ICML, ICLR, FAccT, AAAI, ACL, EMNLP, etc.

The exact topics and the work plan of the PhD will be defined together with the selected candidate.

Your profile

Your experience and profile:

• MSc in artificial intelligence, computer science, engineering, mathematics, physics, or a related discipline
• Demonstratable background in machine learning
• Excellent software engineering skills in Python
• Fluent in English, both written and spoken

Our offer
A temporary contract for 38 hours per week for the duration of 4 years (the initial contract will be for a period of 18 months and after satisfactory evaluation it will be extended for a total duration of 4 years). The preferred starting date is as soon as possible. This should lead to a dissertation (PhD thesis). We will draft an educational plan that includes attendance of courses and (international) meetings. We also expect you to assist in teaching undergraduates and master students.

The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 2,872 to € 3,670 (scale P) .This does not include 8% holiday allowance and 8,3% year-end allowance. The UFO profile PhD Candidate is applicable. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants. The Collective Labour Agreement of Universities of the Netherlands is applicable.

Besides the salary and a vibrant and challenging environment at Science Park we offer you multiple fringe benefits:

• 232 holiday hours per year (based on fulltime) and extra holidays between Christmas and 1 January;
• multiple courses to follow from our Teaching and Learning Centre;
• a complete educational program for PhD students;
• multiple courses on topics such as leadership for academic staff;
• multiple courses on topics such as time management, handling stress and an online learning platform with 100+ different courses;
• 7 weeks birth leave (partner leave) with 100% salary;
• partly paid parental leave;
• the possibility to set up a workplace at home;
• a pension at ABP for which UvA pays two third part of the contribution;
• the possibility to follow courses to learn Dutch;
• help with housing for a studio or small apartment when you’re moving from abroad.

Are you curious to read more about our extensive package of secondary employment benefits, take a look here.

About us
The University of Amsterdam is the Netherlands' largest university, offering the widest range of academic programmes. At the UvA, 30,000 students, 6,000 staff members and 3,000 PhD candidates study and work in a diverse range of fields, connected by a culture of curiosity.

The Faculty of Science has a student body of around 8,000, as well as 1,800 members of staff working in education, research or support services. Researchers and students at the Faculty of Science are fascinated by every aspect of how the world works, be it elementary particles, the birth of the universe or the functioning of the brain. Want to know more about our organisation? Read more about working at the University of Amsterdam.

The Institute for Logic, Language and Computation (ILLC) is an interdisciplinary research institute at the University of Amsterdam in which researchers from the Faculty of Science and the Faculty of Humanities collaborate. Research at the ILLC brings together insights from various disciplines concerned with the study of fundamental principles of encoding, transmission, and comprehension of information, such as computer science, AI, computational linguistics, mathematics, logic, philosophy, and cognitive science. The institute offers a friendly and international research environment with world-class faculty in all of its areas of specialisation. Want to know more about our organisation? Read more about working at the University of Amsterdam.

If you feel the profile fits you, and you are interested in the job, we look forward to receiving your application. You can apply online via the button below. We accept applications until and including 31 December 2024.

Applications should include the following information (all files besides your CV should be submitted in one single pdf file):

• Letter of motivation, including a description of your research interests and an explanation for why you are applying for this position (maximum 1 page);
• List of all Master-level modules you have taken, with an official transcript of grades;
• Writing sample, such as a Master’s thesis, a term paper, or a publication (in case of joint authorship, please clearly indicate your own contribution, you can refer to this typology to inform your answer);
• Detailed CV including the months when referring to your education and work experience;
• Applicants are strongly encouraged to include a link to their GitHub repository, portfolio website, or any projects they have designed or developed, showcasing their work, and demonstrating relevant skills.

Please make sure to provide ALL requested documents mentioned above.
You can use the CV field to upload your CV as a separate pdf document. Use the Cover Letter field to upload the other requested documents, including the motivation letter, as one single pdf file. A knowledge security check can be part of the selection procedure (for details: national knowledge security guidelines). Only complete applications received within the response period via the link below will be considered. We will invite potential candidates for online interviews soon after the expiration of the vacancy. If you encounter Error GBB451, reach out to our HR Department directly. They will gladly help you continue your application.

Do you have any questions or do you require additional information? Please contact:

• Dr. Ana Lucic (a.lucic@uva.nl). Please quote “PhD Position” in the email subject for requesting information.