AI Algorithm Engineer (Multi-omics & Health Prediction)

Quantum Life is developing an AI modeling initiative that leverages large-scale population cohorts, clinical measurements, and multi-omics data to characterize human aging, predict future health trajectories, and assess disease risk.

We are seeking an AI Algorithm Engineer with expertise in machine learning, statistical modeling, or bioinformatics to develop and improve models for organ-specific biological age, health-state estimation, and disease risk prediction. You will apply deep learning, statistical learning, survival analysis, and longitudinal modeling to extract meaningful patterns from high-dimensional biological and clinical data and build robust predictive models that generalize across populations and cohorts.

This role connects molecular and cellular research with human health outcomes, helping establish the computational foundation for longitudinal health prediction, personalized health modeling, and future intervention research.

Job Description

Key Responsibilities

1. Health and Organ Age Modeling

   • Develop and optimize machine learning models for biological age estimation, organ-specific aging, and health-state characterization.
   • Explore methods including Elastic Net, gradient-based models, deep neural networks, and other appropriate statistical or machine learning approaches.
   • Identify informative molecular and clinical features associated with aging and organ-specific health conditions.

2. Longitudinal Health and Disease Prediction

   • Develop predictive models using longitudinal clinical records, population cohorts, and multi-omics datasets.
   • Apply survival analysis, longitudinal regression, and time-to-event modeling to predict future disease outcomes and health trajectories.
   • Investigate how changes in biomarkers and biological age relate to subsequent health outcomes.

3. Multi-omics and Clinical Data Modeling

   • Integrate relevant molecular features, clinical biomarkers, demographic variables, and longitudinal phenotypes.
   • Develop robust data preprocessing, feature engineering, model training, and evaluation pipelines.
   • Investigate strategies for handling missing data, cohort heterogeneity, and differences in measurement protocols.

4. Model Validation and Generalization

   • Design rigorous validation strategies, including held-out testing and external cohort validation.
   • Evaluate discrimination, calibration, prediction error, and robustness using metrics appropriate to each task.
   • Identify sources of dataset shift and improve model generalization across cohorts and populations.

5. Research Collaboration and Model Translation

   • Collaborate with CORTEX-Cell and CORTEX-Causal researchers to connect molecular mechanisms with human aging phenotypes and clinical outcomes.
   • Translate research questions into well-defined modeling tasks and measurable validation criteria.
   • Document model performance, analytical methods, and scientific findings to support research development and downstream applications.

Qualifications

• Master's degree or above in Computer Science, Artificial Intelligence, Biostatistics, Bioinformatics, Computational Biology, or a related field.
• Solid understanding of machine learning, statistical modeling, and predictive model evaluation.
• Proficiency in Python and relevant libraries such as PyTorch, scikit-learn, pandas, or equivalent tools.
• Experience in at least some of the following: deep learning, regression, survival analysis, longitudinal modeling, or high-dimensional data analysis.
• Ability to work with complex datasets, design rigorous experiments, and interpret model performance critically.

Preferred Qualifications

• Experience with biomedical, clinical, epidemiological, or multi-omics datasets.
• Familiarity with biological age estimation, organ-specific biomarkers, disease risk prediction, or aging research.
• Experience with external validation, cohort harmonization, or population-level predictive modeling.
• Knowledge of causal inference, temporal modeling, or interpretable machine learning.
• Research publications or experience developing models for real-world scientific or healthcare applications.

What We Offer

• The opportunity to develop predictive AI models using large-scale human health and multi-omics data.
• Direct involvement in research connecting biological aging with future health outcomes.
• Collaboration across AI, computational biology, and causal discovery teams.
• The opportunity to contribute to scientific research and the development of next-generation longevity modeling technologies.