Founding Computational Biologist

Please include:

• Your CV
• Your LinkedIn profile URL
• Links to any relevant public work (GitHub, Hugging Face, Google Scholar, personal site, etc.)
• Optionally, a short paragraph about what attracted you to this role Founding Computational Biologist – Computational Biology & AI Platform

You would be the first scientist in Valvian's Computational Biology & AI function, working directly with the Head of Computational Biology & AI. We are building a computational platform that brings together AI models and proprietary experimental data to find the targets and drug candidates in oncology and age-related disorders that the existing knowledge does not make obvious. The first major challenge sits upstream of any AI model.

In our therapeutic area, the evidence is scattered across different public resources, primary literature and internal experimental data, reported inconsistently, and deeply dependent on experimental context that is rarely recorded. Whether a data substrate is structured, provenance-aware and honest about uncertainty determines whether anything built on top of it can be trusted. A model trained on unstructured data across the literature learns the shape of that literature and its biases rather than the underlying biology.

That structured data substrate is the core of the role. What should the data model look like? Which observations can legitimately be compared? How should conflicting evidence be represented rather than quietly reconciled? How are different entities dependent on each other? How do we unify existing data with our own? You would help answer those and other questions, then implement the pipelines and processes to populate, maintain and expand this resource as it becomes a reliable substrate for the implementation of predictive AI models.

Because the function is new, the work is unusually broad. You would have active participation in developing the full platform, i.e. the data model, the pipelines, the curation, the automations, and the conversations with the bench, rather than owning one narrow slice of an existing system. About Valvian

Valvian is a Lisbon-based biotechnology company developing next-generation therapeutics for cancer and age-related disorders. We exist because cancer and the diseases of ageing remain among the largest sources of human suffering, and the conventional drug-discovery playbook has been slow to close the gap. Our bet is that better therapeutics will come from a tighter integration of disease biology, translational biomarkers and computational pipelines.

In oncology, our focus is solid tumours, where antigen complexity, the tumour microenvironment and immune evasion demand careful modality selection, safety-by-design and biomarker-driven translation. Our portfolio includes antibodies and cell therapies designed specifically for solid-tumour constraints. In age-related disorders, we work on the system-level biology of ageing: immune ageing, chronic inflammation, progressive tissue dysfunction and cellular senescence, with biomarker anchors that make each programme development-ready.

Key Responsibilities

Data foundations

Take raw, messy experimental and public data through to something usable: ingestion, cleaning, structuring, and the judgement calls that go with it. Build and maintain the pipelines and tools the rest of the team depends on, with version control, environment management, reproducibility and testing where it matters from the start. Work in modern cloud infrastructure, with attention to GDPR compliance and data sovereignty from day one. Evidence model and curation

Help design the data model that holds our evidence: the entities, relationships, controlled vocabularies and confidence scales that let a claim be assessed rather than assumed, and then curate against it at volume. Integrate heterogeneous data while preserving experimental context, provenance and uncertainty, so that what a measurement actually means survives the act of storing it. Systematically evaluate public biological databases against a common specification, establishing what each can and cannot support, and what integrating it would genuinely cost. Surface contradictions between sources rather than resolving them silently. Automated and agentic workflows

Design and evaluate semi-automated extraction of evidence from scientific literature, including deciding how such a system should be scored and where it should not be trusted. Treat model outputs as scientific inputs rather than finished answers, with explicit measurement of where they succeed and fail. Help build the first predictive models on top of the evidence layer, and design validation that tests whether they generalise to cases they have not seen rather than reproducing what they were shown. Scientific partnership

Work directly with our lab scientists on what their da