Caeruleus is redefining the boundaries of precision medicine. Harnessing advanced machine learning and proprietary single-cell sequencing technologies, we’re pioneering a new era of therapeutic discovery beyond traditional gene expression analysis. Our revolutionary platform is transforming target discovery to develop medicines for millions of patients with unmet clinical needs. We are venture financed by global investors and supported by experienced company builders.
The Opportunity
We seek a Founding Machine Learning Engineer to join our computational team and lead the development of cutting-edge deep learning systems tailored for a novel type of single-cell sequencing data. This role offers the chance to make a direct impact by designing scalable solutions, conducting advanced research, and shaping the future of AI in precision medicine. As an early team member, you will be critical in building the company’s computational foundation and driving scientific discovery.
Responsibilities
- Conduct advanced machine learning research, contributing to developing novel model architectures and new approaches for single-cell data analysis.
- Build scalable ML data pipelines, ensuring efficient pre-processing, training, and inference for large biological datasets.
- Optimize and benchmark deep learning models for performance, robustness, and scalability.
- Collaborate across disciplines to integrate experimental feedback into computational models and refine scientific strategy.
- Publish findings (e.g. NeurIPs, ICML, Nature), contribute to open-source projects, and mentor junior team members.
Key Experiences:
- Research Excellence: Strong ML research experience with a proven track record of high-impact publications (e.g., NeurIPS, ICML, ICLR, Nature) or significant contributions to open-source libraries or industry projects.
- ML Engineering Expertise: Experience building and deploying scalable ML data pipelines and optimizing and benchmarking deep learning models for performance. Experience with advanced model architectures such as graph neural networks (GNNs), BERT, or variational autoencoders (VAEs).
- Bio AI interest: Experience with data structures and methods for working with sparse, raw single-cell sequencing data and interrogating processed datasets (graph and causal methods, LLMs).
- Basic Software Development: Proficiency in modern software tools, including version control, code reviews, and MLOps workflows. A demonstrable passion for writing clean, robust, and maintainable code.
- Cloud and HPC Proficiency: Experience deploying ML models in cloud or high-performance computing environments.
Who you are?
- PhD or Postdoctoral researcher in physics, computer science, machine learning, mathematics, complexity theory, statistics or computational biology.
- [Desireable] Some level of industry technical start-up experience as evidenced through internships or pre/post-doctoral work.
OR A Master's in the above subjects with 3-4 years of industrial experience in a relevant competitive environment.
- Proficiency in Python, Dask, Numpy, Pandas, Keras and PyTorch.
- Experience with single-cell sequencing data
- Passion for knowledge sharing, mentoring colleagues, and shaping scientific strategy as part of a growing leadership team.
What We Value
- Scientific Excellence: Transparency and rigor drive us. Every result—positive or negative—is a step forward.
- Extreme Ownership: We take responsibility, solve problems, and get things done.
- Impact-Driven: We are motivated by the difference we can make for patients and science.
- Kindness: Flexibility, respect, and personal agency define our approach to teamwork.
- Ambition: We aim high, investing in ourselves and each other to achieve extraordinary goals.
- Add a Zero: We embrace technology and new methods to amplify our impact and resources.
Compensation and Benefits
• Salary: Competitive, including founder-level equity.
• Benefits: Health insurance, pension contributions, generous holiday allowance, and flexible working options.
• Professional Development: Opportunities to publish research, attend conferences, and access a training budget.
• Location: Oxford or London (UK), with in-person collaboration preferred (remote fine in the short to mid-term)
Top Skills
What We Do
Caeruleus is a biotechnology company that decodes the hidden story of human biology beyond gene expression. Spun out from Oxford University by experts in functional genomics, target discovery and computational biology.
