Explainable AI for Protein Language Models & Physics-Based Generative Folding

SFBI; Valbonne; On-site; EUR 25,000 - 29,000; Full time

Benefits offered by this job

Access to Grid’5000 HPC resources

Collaborative research environment at

Job summary

SFBI seeks a postdoctoral researcher to advance explainable AI for protein language models and physics-based folding. You will lead the inaugural explainability study of pLM failures and contribute to novel flow-matching-based predictors, working with a team at Inria Sophia Antipolis near Nice.

The role requires a PhD in relevant fields, strong DL skills, and proficiency in Python with PyTorch; English communication essential.

Qualifications

• PhD completed or imminent in ML, computational biology, bioinformatics, biophysics, or related field.
• Strong working knowledge of deep learning, including transformer architectures and attention mechanisms.
• Solid Python programming skills and fluency in English with at least one DL framework (PyTorch preferred).
• Ability to work independently, manage a research timeline, and communicate clearly in English.

Responsibilities

• Lead the first systematic explainability study of protein language model failures with residue-level quality labels.
• Develop explainability methods to identify input features and attention patterns driving hallucination events.
• Contribute to conceiving novel flow-matching-based protein structure predictors.
• Lead the XAI track and collaborate on the flow-matching track as needed.

Skills

Deep learning

Transformer architectures

Attention mechanisms

Python programming

English writing

Education

PhD in ML/biophysics/biocomputing

Tools

PyTorch

Grid’5000 HPC

GPU-accelerated training

Job description

Explainable AI for Protein Language Models & Physics-Based Generative Folding

Description

Why do protein structure predictors confidently produce nonsense, and can we see it coming?

You will lead the first systematic explainability study of protein language model failures, using hallucinated predictions with physically grounded, residue-level quality labels. You will also contribute to conceive novel flow-matching-based protein structure predictors.

About the Project

Protein structure prediction has been transformed by deep learning, yet two fundamental problems remain unsolved.

• Deep-learning structure predictors hallucinate on about 5–10% of their targets – they confidently produce physically implausible outputs whose failure modes are poorly understood and almost entirely opaque [1].
• pLMs rely heavily on the evolutionary signal they absorbed during training: when this signal is weak or missing, as for evolutionarily diverged and de novo proteins, they fall back into hallucinated patterns [2]. This project attacks both problems.

Track 1. On the interpretability side, we are compiling FLoPS, a curated dataset of pLM hallucinations scored with abstraqt [1], an ad-hoc scoring function which provides a physically grounded quality signal at the residue and contact level. Using this dataset, we want to develop explainability methods that identify which input features, attention patterns, and latent representations drive hallucination events, thus contributing to the first systematic XAI study of pLM failure modes grounded in physical plausibility rather than held-out structural benchmarks.

Track 2. On the generative modelling side, we are developing a novel flow matching architecture for protein folding that operates with little or no evolutionary information (homology, coevolution). The model will learn a mixture of physically motivated velocity fields (for secondary structure formation, hydrophobic collapse, and side-chain adjustment) with learned gat-
ing functions that capture the correct hierarchical order of folding events. Training data will consist of kinetically annotated all-atom trajectories generated by enhanced sampling methods (Self-Consistent Path Sampling, Weighted Ensemble) across the CATH fold space. The postdoctoral researcher appointed to this position will lead the XAI track as their primary responsibility,and will have the opportunity to significantly contribute to the flowm atching track as an exploratory, high-risk/high-gain secondary activity, depending on interest and background.

[1] E. Sarti and F. Cazals. “Fold or flop: quality assessment of AlphaFold predictions on whole proteomes”. In: Bioinformatics Advances 6.1 (2026), vbag190. doi: 10.1093/bioadv/vbag190.
[2] E.Seçkin, D.Colinet, E. G. J. Danchin, and E. Sarti.“Evaluating transformer-based models for structural characterization of orphan proteins”. In: Bioinformatics Advances (2026), vbag215. doi: 10.1093/bioadv/vbag215.

What We Offer

Contract: 12 months, with the possibility of renewal for a further 12 months.

• Start date: 4 January 2027, with 1-2 months flexibility if necessary.
• Salary: from 2200€ per month, depending on experience.
• Compute: access to Grid’5000, the French national testbed for large-scale computing, plus local resources.
• Location: Inria Sophia Antipolis, near Nice and Antibes on the Mediterranean coast.

Requirements

• PhD in machine learning, computational biology, bioinformatics, biophysics, or a closely related field, completed or imminent at the time of appointment.
• Strong working knowledge of deep learning, including transformer architectures and attention mechanisms, demonstrated by publications or substantial open-source contributions.
• SolidPython programmingskillsand fluency withatleast one major deep learning framework (PyTorch strongly preferred).
• Demonstrated ability to work independently, manage a research timeline, and write clearly in English.

Nice to have (you don’t need all of these)

• Prior experience with explainability or interpretability methods for large neural networks (attribution methods, probing, mechanistic interpretability).
• Familiarity with protein language models (ESM family, ProtTrans, or similar).
• Experience with generative models: diffusion, flow matching, score matching, or variational autoencoders applied to structured or geometric data.
• Background in statistical mechanics, molecular dynamics, or enhanced sampling, even at a foundational level.
• Experience with HPC cluster environments and GPU-accelerated training.

Candidature

Procédure : Send an email containing:

• A brief description of who you are and what your interests are. Which of the two tracks motivates you most, and why?
• Your CV (PDF format) including a full publication list and links to any relevant code repositories or preprints.