Machine Learning Engineer

We are working with a pioneering deeptech organisation dedicated to transforming the drug discovery and development process in immunology and inflammation. With a unique foundation model dedicated to immune-mediated diseases, the company leverages multimodal data to bridge the gap in translational research, accelerate the validation of new therapeutic targets, and advance the development of personalised treatments.

Backed by significant recent funding and recognised as one of the most promising startups in Europe, this is an opportunity to join a highly collaborative, science-led team at the forefront of AI in healthcare.

This role will offer you:

• The opportunity to design and optimise transformer-based foundation models for biomedical data, including transcriptomics, histology, and large-scale clinical datasets.
• A key role in building scalable ML infrastructure and pipelines to support research and production applications.
• Collaboration with a multidisciplinary team of AI researchers, computational biologists, and immunologists.
• A chance to contribute to cutting-edge science featured in top-tier journals and international congresses.

Responsibilities:

• Develop, implement, and fine-tune ML models, with a focus on pre-training, fine-tuning, and benchmarking at scale.
• Build and maintain scalable ML pipelines, including data preprocessing, model training, evaluation, and deployment.
• Apply MLOps best practices, ensuring model versioning, monitoring, and reproducibility.
• Transform raw biomedical datasets into deep-learning-ready loaders capable of scaling to millions of datapoints.
• Collaborate closely with scientific experts to align AI approaches with biological questions and translational applications.

You will bring:

• Master’s degree or PhD in Machine Learning, Computer Science, Data Science, or a related field.
• 3+ years’ experience with deep learning frameworks (PyTorch, TensorFlow, JAX).
• Strong Python skills and experience in production ML systems, including containerisation (Docker), orchestration (Kubernetes), and cloud platforms (AWS, GCP, Azure).
• Hands-on experience with MLOps frameworks (Kubeflow, MLflow, Weights & Biases, Metaflow) and modern DevOps practices.
• Experience with distributed training, GPU programming, and model optimisation techniques.

How to stand out:

• Experience with biological or healthcare data, especially transcriptomics or histology.
• Background in foundation models (NLP or multimodal).
• Strong adaptability and motivation to work in a dynamic, fast-growing startup environment.
• A team-oriented mindset with high agency and problem-solving skills.