Intern, Computational Biology (Spatial Gene Expression)

About the role:

The Computational Biology group at 10x Genomics is looking for an outstanding intern to work with us in the summer of 2025. This person will develop high-performance models to predict spatial gene expression from tissue images. They will work closely with our imaging and assay-development teams to push the state-of-the-art in spatial transcriptomics. The intern will be involved in selecting, implementing, testing, and optimizing models to extract relevant information from tissue images, rapidly prototyping methods for internal experiments and early R&D.

Interns will work on a mix of “real-world” product features that will ship to customers soon, and longer-term exploratory proof-of-concept work to test new ideas.

Individuals applying for this position should have a strong background in computer vision and machine learning. You have a deep understanding of the theory, implementation, and practical application of various relevant algorithms. You can take an idea, quickly implement it in code, and evaluate its performance. You must be self-starters, strategic thinkers, action driven, and thrive in a fast paced environment.

Key Opportunities

• Select, implement, test, and optimize prediction methods to extract relevant information from imaging data.
• Rapidly prototype methods for internal experiments & early R&D
• Build analytical models or simulations to understand and communicate key trade-offs of model design and data quality.
• Create high-quality and robust implementations of production algorithms.

Required Skills and Background

• Currently enrolled in a M.S. or Ph.D program in computer science, computational biology or a related field
• Strong skills in image processing (feature extraction, object detection & classification, segmentation, etc.), including both classical algorithmic approaches and deep learning.
• Strong programming ability in Python or Rust/C/C++
• Ability to research existing methods from literature, adapt them to the problems at hand,  and turn them into well architected code.
• A combination of mathematical depth with a healthy respect for the imperfections inherent in real-world data.
• Experience with cell, fluorescence, and/or histology imaging is a plus.