PhD in computational biology, bioinformatics, computer science, or a related field
0-5 years industry or academic training for Scientist; 5+ years for Senior Scientist
Strong publication record
Deep expertise in machine learning and statistical algorithms
Knowledge of molecular biology and genetics with familiarity in genomic data
Experience in analyzing genomics sequencing data, particularly single-cell assays
Fluency with AI-assisted development tools and modern research practices
Responsibilities
Design and train deep learning models for biological sequence analysis
Collaborate with experimental scientists to validate model predictions
Analyze large-scale genomics data for actionable insights
Translate computational findings into biological context
Publish research and develop open-source software and public tools
Benefits
Eligible for two annual cash bonuses
Opportunity to work at the forefront of computational biology
Collaborative environment with access to experimental science
Exposure to cutting-edge research in deep learning and genomics
Proximity to leading researchers in the field
Full Job Description
Position Description:
Calico is seeking a machine learning scientist to join a research group investigating how genome sequence determines regulatory function and how dysregulation of these programs drives aging. We develop sequence-based deep learning models that predict gene expression, chromatin accessibility, and other functional readouts directly from DNA. We use these models to interpret human genetic variation, map causal regulatory mechanisms, and identify promising intervention points.
This work builds on a sustained research program at the intersection of deep learning and regulatory genomics, including:
Avsec, Ž. et al. Effective gene expression prediction from sequence by integrating long-range interactions. Nat Methods 18
Yuan, H. & Kelley, D. R. scBasset: sequence-based modeling of single-cell ATAC-seq using convolutional neural networks. Nat Methods 19
Linder, J., Srivastava, D., Yuan, H., Agarwal, V. & Kelley, D. R. Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation. Nature Genetics (2025).
Additional research can be found here.
Position Responsibilities:
Design and train deep learning models for biological sequence analysis, with emphasis on gene regulation, single-cell genomics, and variant interpretation
Partner with experimental scientists to connect model predictions to biological mechanisms - designing validation experiments, analyzing large-scale genomics data, and translating computational findings into actionable biological insights
Communicate research through publications, open-source software, and public-facing tools
Position Requirements:
PhD in computational biology, bioinformatics, computer science, or a related field, and 0-5 years (for Scientist level) or 5+ years (for Senior Scientist level) of additional training in an industry or academic setting, with a strong publication record
Deep expertise in machine learning with solid grounding in algorithms, data structures, and statistics
Substantive knowledge of molecular biology and genetics; familiarity with genomic data types and public data resources
Hands-on experience analyzing genomics sequencing data, ideally including single-cell assays
Fluency with modern AI-assisted development and research tools (e.g., LLM-based coding assistants, literature synthesis), with a habit of proactively integrating new tools to accelerate scientific workflows
A collaborative disposition, strong follow-through, and comfort working at the interface of computation and experiment
Must be willing to work onsite at least four days per week
The estimated base salary range for this role is $170,000 - $233,000. Actual pay will be based on a number of factors including experience and qualifications. This position is also eligible for two annual cash bonuses
