We are looking for a Senior Machine Learning Scientist to help turn biological and experimental data into predictive models.

Company

Bactobio is a London biotech startup. We work to solve the antimicrobial resistance crisis across healthcare and agriculture by producing the next generation of market-leading antimicrobials. Since inception in 2020, Bactobio has built a deeptech platform that combines AI, synthetic biology, and multiomics to routinely discover new antimicrobial classes from nature. Our antimicrobial platform is fully operational, and we now successfully target the worst diseases and build portfolios of new, safe, and effective antimicrobial classes that bypass resistance that we then move towards commercialisation.

Our culture is built around impact, empowerment, and collaboration. We attract incredible scientists from world-leading institutions, mix them with operational experts, and provide guidance through industry leaders acting as mentors. We strongly believe that diversity combined with open and inclusive conversations lead to better solutions. As a result, we have created a collaborative work environment, where ambitious people enjoy working together to make the world greener and safer.

Role

This is a senior, high-impact role at the heart of our discovery engine. The models that you build will shape what we test next to help turn biological and experimental data into predictive models. You’ll work across bioinformatics, wet lab science, and software to make machine learning a practical driver of scientific progress.

You’ll thrive here if you’re passionate about the intersection of AI and biology, you’re motivated to push boundaries, and you want your work to be tightly connected to real experiments, real decisions, and real outcomes. You won’t just be a cog in the machine. Rather, you’ll be a creative technical voice with meaningful ownership.

This is an applied research role that ships real code. We explore new ML ideas and approaches with the goal of turning insight into something that runs, gets used, and moves our platform forward.

Team

You’ll be joining a vibrant, tight-knit, and highly collaborative team of about fifty people. We sit and work together and take genuine interest in one another's work. Day-to-day, you’ll collaborate with wet-lab and automation scientists, other data scientists, bioinformaticians, and software engineers, with plenty of exposure to the broader company journey too.

Everyone who writes code at Bactobio contributes regularly to the same shared codebase. We care about well-designed data models, best practices with sensible implementations, and building a tech stack that’s productive, maintainable, and genuinely enjoyable to work in.

Key Responsibilities

• Turn high-level scientific goals into precise, data-driven research questions and methodologies.
• Collaborate closely with lab scientists to design experiments to ensure that our data is robust and useful for meaningful ML.
• Work with bioinformaticians and analytical chemists to shape omics and mass spec data for modelling.
• Lead the development of ML methods to model microbial communities and predict metabolite production and activity, including the use of DNA and protein language models (or closely related sequence/foundation models).
• Build, implement, and refine predictive models that accelerate discovery: guiding cultivation efforts, improving metabolite production, and optimising sample selection across various stages of our pipeline.

Skills, Knowledge and Expertise

• A PhD in machine learning, computational biology, bioinformatics, mathematics, or a related STEM field, or at least four years of ML-focussed industry experience.
• Strong research or industry track record applying ML in biotech or adjacent scientific settings.
• Deep understanding of statistical modelling and ML methods, and good judgement about when to use what.
• Experience designing, training, and fine-tuning sequence models (genomic/proteomic language models, or closely related architectures).
• Advanced proficiency in Python, with substantial experience in modern ML and data science tooling.
• Comfort working with biological data (omics, sequences, experimental metadata) and collaborating with domain experts.
• Proven experience shipping high-quality code in a collaborative environment, including readable, production-ready implementations.

Benefits