Senior Data Scientist - AI & Genomics

About Us 

At DNAstack, our mission is to power precision medicine by building software that breaks down barriers to responsible biomedical data sharing, discovery, and analysis. We develop cutting-edge technologies and industry standards to help researchers and clinicians analyze sequencing data and make faster, more accurate diagnoses. Our platform supports national and international networks tackling rare disease, cancer, infectious disease, and more. We’re a small but mighty startup team working at the intersection of bioinformatics, cloud computing, and open science.

The Role 

We’re looking for an experienced Senior Genomics Data Scientist to join our nimble bioinformatics and AI team. This role is focused on the development and application of AI-driven data science techniques to support bioinformatics and tertiary workflows across a federated network. You’ll be responsible for designing, optimizing, and maintaining AI-powered analytical methods to extract insights from large-scale genomic data.

You’ll work both independently and directly with our research and clinical partners, applying your knowledge of genomics, machine learning, and data science best practices to develop scalable, intelligent models for genomic interpretation. You’ll help shape our AI strategy, integrate novel machine learning models into genomic workflows, and play a major role in advancing federated bioinformatics capabilities.

What You’ll Be Doing

• Develop and apply AI-powered data science methods for analyzing large-scale genomic datasets in a federated environment.
• Design, train, and validate machine learning and deep learning models for genomics, including variant classification, functional annotation, and disease risk prediction.
• Collaborate with partners in academia and industry to create models that process and harmonize diverse genomics datasets.
• Apply large language models (LLMs) and generative AI for automated annotation, scientific literature mining, and variant impact prediction.
• Utilize federated learning frameworks to train AI models on distributed genomic data while ensuring privacy compliance.
• Support the development of data harmonization and feature engineering pipelines to enhance AI model performance across genomic datasets.
• Communicate complex AI-driven genomic analyses clearly to technical and non-technical stakeholders.
• Stay current with emerging AI and deep learning techniques for genomics, participating in open-source initiatives and advancing industry best practices.
   

What We’re Looking For

• Master’s degree or PhD in data science, computational biology, bioinformatics, AI/ML, biostatistics, or a related field—or equivalent industry experience.
• 4+ years of hands-on experience applying data science and machine learning techniques to genomics datasets.
• Strong experience implementing AI-powered bioinformatics tools and applying machine learning techniques to genomic analysis.
• Proficiency with deep learning models for genomics such as AlphaFold, ESMFold, OpenFold, DeepSEA, and Enformer.
• Experience with LLMs for genomic applications, including automated annotation and text-based variant interpretation.
• Strong programming skills in Python (preferred), R, or Julia, with experience using AI/ML libraries such as TensorFlow, PyTorch, or scikit-learn.
• Expertise in working with large-scale genomic datasets, including WGS, WES, RNA-seq, and methylation data.
• Familiarity with cloud computing (GCP, AWS, or Azure) or HPC environments.
• Experience leveraging federated learning and privacy-preserving AI for genomic data sharing.
• Strong interpersonal and communication skills—able to translate between technical, scientific, and clinical domains.
• Statistical and visualization skills for exploring -omics datasets.
   

Nice to Have

• Experience with clinical genomics, ACMG variant interpretation, or diagnostic AI pipelines.
• Experience developing workflows using WDL, CWL, Nextflow, or Snakemake.
• Familiarity with public genomics datasets (e.g., gnomAD, TCGA, ENCODE) and FAIR data principles.
• Hands-on experience with reinforcement learning and self-supervised learning for genomics applications.
• Experience applying zero-shot or few-shot learning for novel variant prediction and annotation.
• Background in causal inference and graph-based AI for biological networks.

Why Join DNAstack?

• Work on meaningful projects that help improve patient outcomes.
• Be part of a collaborative, mission-driven team in a growing startup.
• Flexible hours and remote-friendly culture.
• Competitive salary, benefits, and stock options.
• Opportunity to contribute to open science and global data-sharing efforts.

Let’s Talk

If this role sounds like a fit—and you’re excited to help shape the future of genomic medicine—we’d love to hear from you. Send us your resume and a short note about why you’re interested.