Deep Learning Research Scientist - Foundation Model on Omics data

DeepLife Group; Paris; Sur place; EUR 90 000 - 150 000; Plein temps

Résumé du poste

DeepLife Group in Paris is seeking a visionary researcher to develop novel cell embeddings by integrating multi-omics foundation models (transcriptomics, proteomics, epigenomics, metabolomics) to capture complex cellular signatures for drug discovery.

You will lead large-scale deep learning, enable digital twin applications, collaborate across disciplines, and translate AI advances into impactful results for clients and partners.

Qualifications

• PhD or postdoctoral experience in computer science or a closely related field.
• Proven expertise in machine learning and applied mathematics.
• Experience with large-scale deep learning on omics or high-dimensional data.
• Proficiency in probabilistic graphical models and causal inference.”
• Ability to lead interdisciplinary collaboration and communicate results clearly.

Responsabilités

• Design and implement large-scale deep learning models that integrate multi-omics datasets.
• Develop and refine foundation models across omics platforms.
• Build and advance digital twin technology for predicting drug effects.
• Collaborate with omics, bioinformatics, and drug discovery teams.
• Lead and publish research efforts within an international team.

Connaissances

Visionary researcher

Multi-omics data integration

Deep learning

Foundation models

Probabilistic graphical models

Causal inference

Cross-disciplinary collaboration

Formation

PhD or Postdoctoral experience in Computer Science

Outils

Python

PyTorch

TensorFlow

JAX

Description du poste

Overview

In this role, you will develop a novel cell embedding that integrates multiple omics foundation models such as transcriptomics, proteomics, epigenomics, and metabolomics to capture comprehensive, multi-dimensional cellular signatures. Your innovations will be pivotal in predicting drug effects on cell types and tissues, transforming raw data into actionable insights in drug discovery.

Key Responsibilities

• Deep Learning Model Development: Design and implement large-scale deep learning models that integrate diverse omics datasets to build robust cell embeddings. These embeddings will serve as the foundation for our digital twin technology, enabling precise predictions of drug effects at both cellular and tissue levels.
• Multi-Omics Integration: Develop and refine foundation models across various omics platforms, combining them into a unified cell embedding that reflects the complex molecular landscape of cells.
• Digital Twin development: Design and implement large-scale causal model to predict cell response to perturbations.
• Cross-Disciplinary Collaboration: Partner with experts in omics, bioinformatics, and drug discovery to ensure seamless integration of multi-modal data and validate model predictions through collaborative research efforts.
• Client & Partner Engagement: Work closely with the product and service teams on projects with clients and strategic partners, translating advanced AI models into impactful drug discovery solutions.
• Research Leadership: Continuously monitor emerging trends in AI and omics technologies, contributing to scientific publications and driving innovation within our international, interdisciplinary team.

What We're Looking For

• A visionary researcher passionate about leveraging deep learning to solve complex biological challenges in drug discovery.
• Proven expertise in integrating multi-omics data to develop innovative computational models that generate actionable insights.

Qualifications (Ranked by Importance)

• PhD or Postdoctoral Experience in Computer Science: Demonstrated expertise, evidenced by publications in top-tier machine learning conferences (e.g., NIPS, ICLR, ICML, UAI, CVPR).
• Strong Foundation in Machine Learning/Applied Mathematics: Robust academic background in advanced ML techniques and applied mathematics.
• Experience with Large-Scale Deep Learning Models: Proven track record in building and scaling AI models, particularly those applied to omics or other high-dimensional biological data.
• Experience with Probabilistic Graphical Models and Causal Inference: Proven track record in designing, building, and scaling advanced causal inference frameworks, including Bayesian networks, structural equation models, and counterfactual analysis methods.
• Multi-Omics Integration Expertise: Experience in developing and combining foundation models across different omics datasets to create unified cell embeddings.
• Collaborative Mindset: Prior success working within interdisciplinary teams and managing cross-functional projects.

Why Join DeepLife?

At DeepLife, you'll be at the forefront of a transformative era in drug discovery. By pioneering multi-omics cell embedding techniques, you'll help shape the future of personalized medicine and digital twin technology in biology. Enjoy the creative freedom to innovate, work alongside international experts, and contribute to projects that have a direct impact on human health.