Machine Learning Engineer

Build production AI systems used by real drug discovery teams. We are partnering with an emerging AI-native drug discovery company looking to hire a Machine Learning Engineer to help scale the predictive infrastructure behind its molecular design platform. This is a rare opportunity to join an early-stage team where your work will directly influence how chemists design, evaluate, and progress molecules across active therapeutic programmes. The role is particularly suited to engineers who enjoy building production ML systems in scientific environments and want to work on real-world problems rather than isolated research projects. This role is full-time and on-site.

Our client is specifically looking for candidates who combine strong machine learning capability with hands-on software engineering experience and exposure to chemical or molecular datasets. This is not a purely academic research role. The focus is on building scalable infrastructure, deploying models, and improving prediction systems used in production.

The company is an AI-native drug discovery platform focused on improving decision-making across medicinal chemistry and molecular design. The business has built a proprietary platform combining experimental molecular property data from patents, publications, partners, and internal sources to support predictive modelling in drug discovery that has gained adoption across global chemistry teams working in oncology, inflammation, dementia, and broader therapeutic areas. The company operates from central London with a collaborative, high-ownership culture combining expertise across machine learning, software engineering, chemistry, and biology.

• Build and deploy molecular property prediction models using real-world chemical datasets.
• Develop and improve ML infrastructure including training pipelines, experiment tracking, model registries, and CI/CD workflows.
• Support production deployment of machine learning systems and scalable cloud infrastructure.
• Curate, process, and validate molecular datasets for predictive modelling.
• Collaborate with scientists, engineers, and end users to deliver practical product-focused solutions.
• Improve model validation strategies, monitoring, and performance evaluation.
• Contribute to scalable scientific software and platform architecture.
• Prepare technical documentation and support scientific presentations where required.

The successful candidate will ideally demonstrate:

• Industry experience building and deploying machine learning systems in production environments.
• Strong software engineering fundamentals and experience shipping production code.
• Hands-on experience with MLOps tooling, model serving, containerisation, and cloud infrastructure.
• Experience applying machine learning within chemistry, molecular property prediction, cheminformatics, or related scientific domains.
• Strong understanding of ML fundamentals including validation strategy, overfitting, and model performance evaluation.
• Ability to work collaboratively across engineering and scientific teams.

Additional experience of interest includes:

• AWS, GCP, or Azure infrastructure experience.
• Infrastructure-as-code and scalable deployment workflows.
• Open-source scientific software contributions.
• Exposure to RDKit, PyTorch, OpenMM, or related tooling.
• PhD or advanced academic background in chemistry, computational chemistry, computer science, or related disciplines.

• Competitive salary and equity options package.
• Opportunity to shape core ML infrastructure within a growing AI drug discovery platform.
• Private medical insurance.
• Pension scheme.
• One week remote working per quarter.
• Frequent company socials and team off-sites.
• Cycle to Work scheme.