Post-Doctoral Research Visit F/M Why Do Protein Structure Predictors Confidently Produce Nonsense, and Can We Anticipate These Failures?

Inria Sophia Antipolis

Valbonne

In loco

EUR 45.000 - 60.000

Tempo pieno

14 giorni+

Aumenta le possibilità di ricevere una risposta da questo datore di lavoro

Il tuo curriculum e una lettera di presentazione personalizzati, che corrispondono esattamente a ciò che sta cercando.

Supera i filtri ATS

Descrizione del lavoro

Inria Sophia Antipolis on the French Riviera invites applications for a research position focused on explaining hallucinations in protein language models. The successful candidate will design analytical methods linking model-internal signals to physical plausibility using the FLoPS dataset and abstraqt annotations.

You'll collaborate with a cross-disciplinary team in machine learning, bioinformatics, and biophysics, develop reproducible code in Python with PyTorch, and contribute to scientific

Competenze

  • Data and model failure analysis: use the FLoPS dataset and abstraqt quality annotations to characterize hallucinations at the residue and contact levels.
  • Explainability method development: adapt and develop attribution methods, attention mechanism analyses, representation probing, and latent-space analysis techniques for protein language models.
  • Failure mechanism identification: investigate relationships between sequence features, internal representations, and violations of physical plausibility constraints.
  • Hallucination detection and anticipation: assess whether internal model signals and explainability methods can identify unreliable predictions, particularly when evolutionary information is limited.
  • Experimental evaluation: design comparative experiments, define appropriate metrics, conduct statistical analyses, and assess the robustness and reproducibility of results.
  • Scientific computing and software development: implement methods in Python, primarily using PyTorch, and leverage available computing resources for large-scale analyses.
  • Scientific dissemination: prepare research papers, present findings at scientific meetings and conferences, and contribute to the dissemination of reproducible code and experimental protocols.
  • Exploratory contribution to generative modelling: depending on expertise, contribute to the design and evaluation of flow‑matching-based protein structure predictors incorporating physically motivated mechanisms of structural formation.

Mansioni

  • Collaborate with the research team on the development, analysis, and exploitation of the FLoPS dataset.
  • Develop and benchmark explainability methods tailored to protein language models and physical plausibility annotations.
  • Design rigorous and reproducible evaluation protocols to identify mechanisms associated with hallucinations.
  • Contribute to interdisciplinary scientific discussions at the intersection of machine learning, bioinformatics, and biophysics.
  • Depending on expertise and project needs, contribute to methodological developments in flow matching and protein structure prediction.
  • Disseminate research outcomes through scientific publications, presentations, and, where possible, the sharing of reproducible code and resources.

Conoscenze

Fluent English

Descrizione del lavoro

Context

Deep learning has transformed protein structure prediction. However, current models can still produce physically implausible structures with high confidence. These failures, known ashallucinations, remain poorly understood and raise fundamental questions about the reliability, interpretability, and limitations of protein language models (pLMs). This project aims to systematically characterize these failures and develop methods to understand and anticipate them. It builds on FLoPS, a dataset of hallucinated protein language model predictions, with physically grounded quality annotations generated using the abstraqt method. These annotations provide residue- and contact-level information, going beyond conventional metrics based on comparisons with reference structures.

The position is based at Inria Sophia Antipolis on the French Riviera, within an interdisciplinary research environment at the intersection of machine learning, bioinformatics, and biophysics. The successful candidate will have access to local computing resources and Grid’5000, the French national testbed for experimental research in distributed computing and high-performance computing.

Main objectives
  • Develop a systematic explainability methodology for protein language model failures, grounded in residue- and contact-level physical plausibility annotations.
  • Identify input features, internal mechanisms, and latent representations associated with hallucinations.
  • Investigate whether model failures can be detected or predicted from internal signals and model outputs.
  • Depending on the candidate’s background and scientific interests, contribute to the design of flow-matching-based generative protein structure predictors that rely less heavily on evolutionary information.
Position highlights:
  • an emerging research topic with strong scientific potential, access to physically annotated data, opportunities to develop novel explainability methods for large neural networks, and the possibility of contributing to generative protein structure modelling.
Assignment

The successful candidate will primarily lead the research track devoted to explaining hallucinations in protein language models. They will design and implement analytical methods that link model-internal mechanisms to the physical quality of predicted structures, using the FLoPS dataset and the annotations generated by abstraqt. They will define experimental protocols, conduct quantitative and qualitative analyses, assess the robustness of the proposed methods, and contribute to the scientific interpretation of the results. Particular attention will be paid to relationships between input sequence properties, model activations and attention mechanisms, latent representations, and the different failure modes observed. The successful candidate will oversee the scientific and technical development of their research, from experimental design to dissemination. They will contribute to scientific publications and the dissemination of methods and results, including the development of reproducible code. Depending on their expertise and interests, they may also contribute, on an exploratory basis, to the project’s second research track: the development of flow‑matching-based protein structure predictors, in collaboration with researchers working on generative modelling and molecular simulation.

Collaboration and responsibilities
  • Collaborate with the research team on the development, analysis, and exploitation of the FLoPS dataset.
  • Develop and benchmark explainability methods tailored to protein language models and physical plausibility annotations.
  • Design rigorous and reproducible evaluation protocols to identify mechanisms associated with hallucinations.
  • Contribute to interdisciplinary scientific discussions at the intersection of machine learning, bioinformatics, and biophysics.
  • Depending on expertise and project needs, contribute to methodological developments in flow matching and protein structure prediction.
  • Disseminate research outcomes through scientific publications, presentations, and, where possible, the sharing of reproducible code and resources.
References

[1] E. Sarti and F. Cazals. “Fold or flop: quality assessment of AlphaFold predictions on whole proteomes”. 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”. Bioinformatics Advances, 2026, vbag215.

Main activities
  • Data and model failure analysis: use the FLoPS dataset and abstraqt quality annotations to characterize hallucinations at the residue and contact levels.
  • Explainability method development: adapt and develop attribution methods, attention mechanism analyses, representation probing, and latent-space analysis techniques for protein language models.
  • Failure mechanism identification: investigate relationships between sequence features, internal representations, and violations of physical plausibility constraints.
  • Hallucination detection and anticipation: assess whether internal model signals and explainability methods can identify unreliable predictions, particularly when evolutionary information is limited.
  • Experimental evaluation: design comparative experiments, define appropriate metrics, conduct statistical analyses, and assess the robustness and reproducibility of results.
  • Scientific computing and software development: implement methods in Python, primarily using PyTorch, and leverage available computing resources for large-scale analyses.
  • Scientific dissemination: prepare research papers, present findings at scientific meetings and conferences, and contribute to the dissemination of reproducible code and experimental protocols.
  • Exploratory contribution to generative modelling: depending on the candidate’s background, contribute to the design and evaluation of flow‑matching-based protein structure predictors incorporating physically motivated mechanisms of structural formation.
Skills

Fluent in English

Ottieni la revisione del curriculum gratis e riservata.

o trascina qui il file.

Similar jobs

Offerte di lavoro simili che vale la pena confrontare

Explainable AI for Protein Language Model Hallucinations
Explainable AI for Protein Language Model Hallucinations

Inria Sophia Antipolis • Valbonne

In loco
EUR 45.000 - 60.000
PhD Position F/M Pretrained models of multimodal neuroimaging for predicting individual cognition
PhD Position F/M Pretrained models of multimodal neuroimaging for predicting individual cognition

Inria Palaiseau • Palaiseau

In loco
EUR 16.000 - 23.000
Research Engineer F/M – Aligning medical foundation models across histology, spatial transcriptomics and MRI
Research Engineer F/M – Aligning medical foundation models across histology, spatial transcriptomics and MRI

Inria Paris • Paris

In loco
EUR 42.000 - 54.000
Research Engineer F/M — Crowd data acquisition, processing and modelling
Research Engineer F/M — Crowd data acquisition, processing and modelling

Inria Rennes • Rennes

In loco
EUR 42.000 - 62.000
Post-Doctoral Research Visit F/M Learning crowd dynamics from real-world data
Post-Doctoral Research Visit F/M Learning crowd dynamics from real-world data

Inria Rennes • Rennes

In loco
EUR 40.000 - 48.000
Engineer F/M - Scientific programmer in federate learning with applications in neuroscience
Engineer F/M - Scientific programmer in federate learning with applications in neuroscience

Inria Villeneuve d'Ascq • Villeneuve-d'Ascq

In loco
EUR 42.000 - 66.000
Senior AI Scientist, Molecular Discovery- F/M
Senior AI Scientist, Molecular Discovery- F/M

Pierre Fabre Laboratories • Toulouse

Ibrido
EUR 60.000 - 80.000
Incentives and profit-sharing
Health and provident insurance
25 days of personal holidays
+1
Research Engineer F/M — Crowd data acquisition, processing and modelling
Research Engineer F/M — Crowd data acquisition, processing and modelling

Inria • Rennes

In loco
EUR 40.000 - 70.000
Partial transport reimbursement
Annual leave + RTT days
Teleworking after 6 months
+4
Post-Doctoral Research Visit F/M Crowd dynamics data acquisition and processing for large-scale dataset construction
Post-Doctoral Research Visit F/M Crowd dynamics data acquisition and processing for large-scale dataset construction

Inria Rennes • Rennes

In loco
EUR 42.000 - 54.000
Research engineer [F/M] for AI-driven molecular and spatial analysis of tumor cell plasticity
Research engineer [F/M] for AI-driven molecular and spatial analysis of tumor cell plasticity

Inria Villeurbanne • Villeurbanne

In loco
EUR 42.000 - 56.000