Postdoctoral Associate (Public Health Sciences)
Core
Develop and evaluate advanced machine learning and deep learning algorithms for analyzing large-scale biological datasets including genomics, transcriptomics, and multi-omics data.
Role type
Postdoctoral Associate in Computational Biology and Bioinformatics
Builds
Production ML models and data analysis pipelines for biological research
Domain
Bioinformatics, Genomics, Computational Biology
Deliverable
production ML models
Required skills
Python, R, Machine Learning fundamentals, Deep Learning architectures (CNNs, RNNs, Transformers), Statistical analysis, Large-scale data handling, Linux environments, Version control (Git), Cloud computing
Preferred skills
Single-cell or spatial omics analysis, DNA Methylation analysis, Graph neural networks, Generative models (VAEs, diffusion models), Multi-modal learning, HPC clusters, GPU acceleration, Bioinformatics tools (FASTQ, BAM, VCF, Seurat)
Technologies
PyTorch, TensorFlow, NumPy, Pandas, SciPy, H5AD, AnnData
Responsibilities
Develop, implement, and evaluate machine learning and deep learning models for biological data analysis; Design data preprocessing and feature engineering pipelines; Perform statistical analyses and model benchmarking; Collaborate with wet-lab scientists to interpret results; Contribute to research manuscripts and conference abstracts
Seniority
Postdoctoral Researcher
