We are constantly looking for exceptional and highly motivated new team members. So don’t hesitate to send your prospective application following these guidelines.
Postdoctoral fellows
We are looking for highly motivated postdoctoral candidates to join us on a scientific journey! We invite candidates that are excited about conducting breakthrough research in machine learning and/or at the intersection of machine learning and biomedicine. The candidates should have a strong computational background. Candidates should have a Ph.D. or equivalent degree in computer science, statistics, applied math, computational biology or a closely related field. Machine learning topics we are especially focused on: domain adaptation/generalization, few-shot learning, unsupervised and semi-supervised learning, graph representation learning, explainable AI, but candidates from other areas are also welcomed to apply. Prior experience in working with biomedical data is not required but a plus.
Application:
To apply, please send the following documents to Maria with the email subject line: “Postdoctoral application”:
-
- CV with a list of your publications
- Research statement (1-2 pages) that describes your prior research and future research plans
- Arrange for at least two letters of reference from your previous research supervisors and collaborators to be sent to Maria
Additionally, you can check out these opportunities for fully funded postdoctoral positions. Feel free to reach out if you are interested in doing research in the lab under these fellowships:
PhD students
We are always looking for highly motivated and talented PhD students. PhD students can join the lab through EPFL’s PhD program in computer science (EDIC) or computational biology (EDCB). The admission process in both programs is centrally handled by EPFL. The system allows you to specify labs you are interested in. ELLIS PhD students still need to be admitted to one of the EPFL’s doctoral programs.
Summer Research Interns
If you are a Bachelor’s or Master’s student, consider applying to the Summer@EPFL internship program. If you are looking for a PhD internship, send Maria an email directly.
Bachelor & Master students
How to apply for Master’s Thesis with Our Lab
If you are an EPFL master’s student interested in conducting your thesis with our lab, send Maria an email including CV and transcripts and use subject line “Master’s Thesis Application”.
How to apply for Bachelor & Master Research Projects
Please apply using the following link. If you are interested in multiple projects, please send only one application and indicate the projects you are interested in the motivation letter.
Below you can find our offerings for Bachelor & Master Research Projects for the 2025 fall semester. (Last update: 11.07.2025) Please, note that the list of topics below is not exclusive. In case you have other ideas or proposals, you are welcome to contact a senior member of the lab and talk about possibilities for a tailor-made topic.
Students interested in doing a project are encouraged to have a look at the Thesis & Project Guidelines, where you will gain an understanding about what can be expected of us and what we expect from students.
- Project 1: Frequent Pattern Mining for Graphs and Point Clouds
Keywords: point cloud pattern discovery, subgraph mining, graph neural network, transformers
Identifying frequent patterns in point clouds or graph motifs is essential for revealing interpretable structural properties of complex networks. Such analyses have significant applications in fields such as biology, social science, and chemistry. However, this is a fundamentally challenging problem due to its combinatorial complexity, especially when dealing with large-scale real-world graphs or point clouds. In this project, we aim to develop a scalable framework for discovering frequent patterns in both graphs and point clouds.
Requirements: We are seeking Master’s students with experience in machine learning. Basic knowledge of single-cell biology is a plus but not required. Applicants should be proficient in Python and familiar with PyTorch for deep learning.
Level: Master
Contact: Yist YU (tingyang.yu@epfl.ch)
- Project 2: Genetic perturbation effect prediction with LLMs
Keywords: Large Language Models (LLMs), Genetic perturbations, Single-cell genomics
Genetic perturbation effect prediction involves forecasting cellular responses, such as changes in gene expression, following targeted gene modifications, including knockouts or CRISPR interference. In single-cell biology, this is crucial for uncovering gene functions, mapping regulatory networks, and identifying cell-type-specific therapeutic targets. Recent advances in high-quality gene knockout datasets have enabled the development of deep learning methods for this task. In this project, we aim to leverage the rich pre-training of large language models (LLMs), which involved extensive single-cell genomics literature present on the internet, to enhance genetic perturbation prediction. Our focus is on developing effective post-training methodologies to unlock and refine the LLMs’ capabilities for this specific application.
Requirement: We are seeking students with experience in post-training of LLMs, particularly with reinforcement learning for LLMs. Experience with single-cell genomics and predicting the effects of genetic perturbations is a plus, but not mandatory.
Level: Master
Contact: Siba Smarak Panigrahi (siba.panigrahi@epfl.ch)
- Project 3: Improving agents for single-cell genomics and biomedical discovery
Keywords: Biomedical Agents, Large Language Models (LLMs), Post-training of LLMs with RL
Recent advances in the reasoning capabilities of large language models (LLMs) have led to the development of agentic frameworks capable of autonomous decision-making across various scientific domains, including single-cell biology. These systems operate through iterative think-act-observe cycles: the LLM plans actions, executes them via a domain-specific environment, and integrates feedback to guide next steps. In single-cell biology, such agents act as collaborative co-scientists, formulating hypotheses, designing validation strategies, and executing complex computational workflows. However, these LLMs often lack domain-specific training before being integrated into agentic workflows. This project aims to improve their reasoning capabilities for single-cell biology tasks through post-training methodologies.
Requirement: We are seeking students with experience in post-training of LLMs, particularly with reinforcement learning for LLMs. Experience with agentic workflows is a huge plus.
Level: Master
Contact: Siba Smarak Panigrahi (siba.panigrahi@epfl.ch)
- Project 4: Multimodal Reasoning – datasets and benchmarks
Keywords: Multimodal Large Language Models (MLLMs), Reasoning
The ability to process and reason through the information from multiple modalities remains a critical challenge in advancing artificial intelligence. However, existing benchmarks focus on text-only reasoning, or include simple multimodal questions that can be easily solved by frontier models. The goal of this project is to build a challenging benchmark for step-by-step, multimodally grounded reasoning. We focus on the tasks that require the crafting and understanding of multistep plans under complex spatial, visual, and physical constraints.
On the other hand, recent visual reasoning models such as GPT-o3 and o4-mini have demonstrated the ability of “thinking with images” within their chain-of-thought trajectories. While this is an exciting achievement, the “thinking with images” behaviors are currently limited to simple visual operations such as cropping or zooming in on the original images. Therefore, we’re also interested in exploring more diverse patterns of visual thinking and developing corresponding datasets/benchmarks to advance this capability.
Requirement: We are looking for students with experience on deep learning and (vision) language models.
Level: Master
Contact: Yulun Jiang (yulun.jiang@epfl.ch)