Refactor and optimize the existing DNA foundation model codebase to ensure maintainability, readability, and scalability.
Develop and implement comprehensive testing strategies to achieve high test coverage.
Design and build a robust, user-friendly API for internal sequence-to-function modeling applications.
Integrate and implement new computational methods and modeling approaches as needed.
Fine tune sequence-to-function models as needed.
Requirements
5+ professional software engineering experience
Proficiency in Python with substantial experience in software development, especially in developing maintainable and scalable codebases.
Demonstrated expertise with PyTorch
Experience working with single-cell omics data and familiarity with established DNA/RNA sequence modeling frameworks (e.g., Enformer, Borzoi) and scverse ecosystem tools.
Self-motivated with excellent communication skills and enthusiasm for contributing to computational biology and software development efforts.
Strong track record of applying software engineering best practices, including version control (Git), comprehensive testing, modular design, and appropriate abstraction levels.