At Freenome, the business and/or technical problem is to develop algorithms for early, blood-based detection tests for cancer by building on ML/DL and statistical skills to develop models for identifying molecular signals from blood.
Requirements
- Expertise demonstrated by research publications or industry achievements, in driving independent research in applied machine learning, deep learning and complex data modeling.
- Practical and theoretical understanding of fundamental ML models like generalized linear models, kernel machines, decision trees and forests, neural networks, boosting and model aggregation.
- Practical and theoretical understanding of DL models like large language models or other foundation models.
- Extensive experience with training paradigms like supervised learning, self-supervised learning, and contrastive learning.
- Proficient in current state of the art in ML/DL approaches in different domains, with an ability to envision their applications in biological data.
- Proficiency in a general-purpose programming language: Python, R, Java, C, C++, etc.
- Proficiency in one or more ML frameworks such as; Pytorch, Tensorflow and Jax; and ML platforms like Hugging Face.
Responsibilities
- Independently pursue cutting edge research in AI applied to biological problems (including cancer research, genomics, computational biology, immunology, etc.).
- Build new models or fine-tune existing models to identify biological changes resulting from disease.
- Build models that achieve high accuracy and that generalize robustly to new data.
- Apply contemporary interpretability techniques to provide a deeper understanding of the underlying signal identified by the model, ideally suggesting potential biological mechanisms.
- Work closely with ML Engineering partners to ensure that Freenome’s computational infrastructure supports optimal model training and iteration.
Other
- PhD or equivalent research experience with an AI emphasis and in a relevant, quantitative field such as Computer Science, Statistics, Mathematics, Engineering, Computational Biology, or Bioinformatics.
- 6+ years of postdoc or post-PhD industry experience achieving impactful results using relevant modeling techniques.
- Excellent ability to communicate across disciplines, work collaboratively, and make progress in smaller steps via experimental iterations.
- Proficient at productive cross-functional scientific communication and collaboration with software engineers and computational biologists.
- A passion for innovation and demonstrated initiative in tackling new areas of research.
