Founding Machine Learning Engineer
Role details
Job location
Tech stack
Job description
This is a founding engineering hire, responsible for building the machine learning systems at the core of the vaccine design platform. The central challenge goes beyond conventional applied ML. The team is modelling an evolutionary interaction between tumours and immune systems, where feedback signals are sparse and experimental ground truth is costly and slow to generate.
The successful candidate will take ownership of model development and infrastructure, shaping both the technical direction and the engineering culture. They will work closely with computational biologists and clinicians to translate complex biological questions into tractable modelling frameworks, and to ensure that methods are robust, interpretable, and deployable.
This role would suit someone motivated by first-principles thinking and difficult prediction problems. A background in areas such as phylogenetics, population genetics, structured probabilistic modelling, or mechanism design would be particularly relevant.
What You'll Do
They will design, implement and iterate on machine learning models that capture evolutionary and immunological dynamics, with a focus on structured prediction and sequence-based data. This includes developing training strategies appropriate for limited and noisy labels, and critically evaluating model assumptions rather than relying solely on benchmark performance.
They will build production-grade systems from research prototypes, establishing clean abstractions and scalable training infrastructure. This includes setting up workflows that make effective use of substantial compute resources while maintaining code quality and reproducibility.
As a founding engineer, they will also influence technical standards, tooling decisions and long-term architectural choices, ensuring that rapid experimentation does not lead to avoidable technical debt.
Requirements
- A strong mathematical foundation, with the ability to read and critically assess methods sections in technical papers.
- Experience developing sequence models, structured prediction systems, or related probabilistic or statistical learning approaches.
- Demonstrated ability to take ideas from exploratory notebooks through to robust, maintainable production systems.
- Fluency in modern ML tooling and the judgement to prioritise sound abstractions over attachment to specific frameworks.
- Intellectual curiosity about complex dynamical systems and inference under limited observation.
Nice to Have
- Exposure to evolutionary dynamics, game-theoretic modelling, phylogenetics, or population genetics.
- Experience working with biological or clinical datasets.
- Prior experience in an early-stage or founding engineering role.
