Postdoctoral Fellowship Positions

Prof. Hima Lakkaraju invites applications for the following Postdoctoral Fellowship positions at Harvard University starting in the Spring/Summer of 2023.

  • Algorithms and Theory for Trustworthy Generative Models: The selected candidate will be expected to lead research in methodological and theoretical advances at the intersection of explainable, fair, adversarial ML, and generative models (e.g., GANs, VAEs, diffusion models, large language models etc.). We seek highly-motivated applicants with background in one or more of the following areas: generative models, explainable ML, adversarial ML, fairness, differential privacy, statistical learning theory. Successful applicants will be strong technically as well as have an inclination towards real-world problems. We are looking for applicants with demonstrably strong research skills, ideally, with multiple publications in top venues in machine learning, artificial intelligence (e.g., ICML, NeurIPS, ICLR, KDD, AAAI, IJCAI, UAI), and/or top-tier interdisciplinary journals (e.g., Nature/Science family of journals, PNAS). Candidates must have a Ph.D. or equivalent degree in computer science, statistics, or a closely related field. Strong programming skills and experience with machine learning and its applications are required.

  • Applied and Human-Centric Aspects of Trustworthy ML: The selected candidate will be expected to lead research in applied and human-centric aspects of explainable, fair, and adversarial ML. We seek highly-motivated applicants with background in one or more of the following areas: explainable ML, adversarial ML, fairness, differential privacy, HCI. Successful applicants will be strong technically as well as have an inclination towards real-world problems. We are looking for applicants with demonstrably strong research skills, ideally, with multiple publications in top venues in machine learning, artificial intelligence, HCI (e.g., ICML, NeurIPS, ICLR, KDD, AAAI, IJCAI, UAI, FAccT, AIES, CHI, CSCW), and/or top-tier interdisciplinary journals (e.g., Nature/Science family of journals, PNAS). Candidates must have a Ph.D. or equivalent degree in computer science, statistics, or a closely related field. Strong programming skills and experience with machine learning and its applications are required.

Application Process

The positions are available immediately and can be renewed annually. Interested applicants should apply via this form and submit the following documents:

  • Curriculum Vitae
  • Link to Github account and/or any software developed
  • Two representative publications (preprints are acceptable)
  • Statement of Research (2 pages) describing prior research experience and future research plans
  • Three letters of recommendation (will be solicited after the initial review)
We are currently reviewing applications for this position. Interested candidates are encouraged to submit their applications as soon as possible and preferably by May 25, 2023. We will continue accepting applications after this deadline if the position is not filled.

PhD Positions

I am looking for motivated students who are interested in contributing to theoretical, methodological, and applied research on explainability, fairness, and adversarial robustness in machine learning. If you would like to pursue a PhD under my guidance, please apply to BOTH the following PhD programs and mention my name in your statements and applications:

  1. PhD Program in Technology and Operations Management at Harvard Business School.
  2. PhD Program in Computer Science at Harvard SEAS.

Internship Positions and Collaborations

We have year-round internship positions available for students who are already doing their graduate studies either in the US or abroad. If this is of interest, please send me an email with your CV and a brief description of your research interests. Please use the subject line "Internship Position (Graduate Student)" in your email.

If you are a current or admitted undergraduate or masters or PhD student at Harvard and would like to work with me, please send me an email with your CV and a brief description of your research interests. Please use the subject line "Interested in Collaboration (Harvard Student)" in your email.

We are also open to collaborating with students and researchers who are already thinking about research problems pertaining to explainability, fairness, and adversarial robustness in machine learning. If you would like to collaborate with us, please send me an email with your CV and a brief description of your research interests. Please use the subject line "Interested in Collaboration" in your email.


Advisor Bio

Prof. Hima Lakkaraju is an Assistant Professor at Harvard University focusing on explainability, fairness, and robustness of machine learning models. At the core of her research lie rigorous computational techniques spanning ML and data mining. She has published extensively on the topics of fair, robust, and interpretable ML in various top-tier ML and AI conferences including NeurIPS, ICML, AISTATS, KDD, AAAI, and AIES. Hima has recently been named one of the 35 innovators under 35 by MIT Tech Review, and was featured as one of the innovators to watch by Vanity Fair. She has received several awards including the best paper awards at SIAM International Conference on Data Mining (SDM) and INFORMS. Her research has also been covered by popular media outlets including the New York Times, MIT Tech Review, Harvard Business Review, TIME, Forbes, Business Insider, and Bloomberg.