Jobs at Relation Therapeutics

Lead Relation's Data Platform team by designing a unified data strategy, optimizing data workflows, and ensuring data governance, while developing a high-performing engineering team.

Design, implement and optimise large neural network models and scalable training pipelines. Build distributed multi-GPU/multi-node training, profile and optimise GPU workloads, maintain core ML infrastructure, and productionise research models for downstream biological discovery workflows.

Develop and validate generative models of cellular behaviour using single-cell and perturbation data. Design models for counterfactual prediction and experimental design, collaborate with experimental teams to test hypotheses, evaluate models for causal and mechanistic fidelity, and communicate results across interdisciplinary stakeholders to accelerate therapeutic discovery.

Design, build, and maintain scalable cloud-native data pipelines and lake/lakehouse infrastructure for multi-modal scientific data. Optimize storage layouts and access patterns for analytics and GPU-based ML training, implement versioning, lineage, and quality monitoring, operate workflow orchestration and containerised environments, and collaborate closely with data scientists and ML researchers to enable efficient model training and research workflows while meeting security and governance needs.

Lead programme-level project management for an osteoporosis discovery programme, coordinating interdisciplinary internal teams and CROs, translating scientific goals into integrated plans, managing budgets, risks, governance, and resource allocation, and communicating status to leaders and partners to drive timely milestone-based progression through discovery stages.

Apply and develop statistical and ML methods for genomics and multi-omics data to support target discovery and validation. Build scalable, reproducible computational workflows, integrate human genetics with OMICs, collaborate with experimental and ML teams, communicate results, and contribute to scientific outputs.

Operate end-to-end single-cell RNA and ATAC sequencing workflows, generate sequencing-ready libraries, ensure QC and metadata tracking in LIMS/ELN, collaborate with automation and computational teams to scale protocols and maintain SOPs and sample traceability.

As a Platform Engineer, develop and manage Kubernetes-based cloud infrastructure, enhance CI/CD pipelines, and collaborate with Machine Learning teams to optimize performance and reliability.

Develop and evaluate machine learning models linking DNA sequence and genetic variation to molecular phenotypes and disease. Build sequence-to-function models (variant effect and regulatory activity prediction), integrate sequence representations with transcriptomic and epigenomic data, collaborate with experimental teams to validate hypotheses, communicate results, and contribute to publications and documentation.