Postdoc: Explainable AI for Protein Language Models & 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

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.