Remote Biomedical Data Scientist - AI-Driven Modeling

Rancho BioSciences; Spain; Remote; EUR 73,000 - 95,000; Full time

Job summary

Rancho BioSciences is seeking a biomedical data specialist to model, harmonize, and curate disease and biomarker data for pharma clients. You will scale AI-ready data products and contribute scientific judgment within an agent-assisted framework.

The role requires deep domain knowledge, strong information modeling, and proficiency with LinkML, Python/SQL, and GitHub. This is a fully remote, client-facing position in Europe.

Qualifications

• PhD in Life Sciences or MS with hands-on biomarker/clinical data experience.
• Strong domain knowledge of biomarkers and disease manifestations.
• Proven data/information modeling experience for complex biomedical domains (ER/class diagrams).
• Experience with LinkML or equivalent schema framework; able to author YAML schemas.
• Experience with biomedical ontologies and controlled vocabularies; mapping data to them.
• Understanding of FAIR principles: persistent IDs, metadata standards, provenance, versioning.
• Hands-on use of AI tools in scientific/data work.
• Ability to review AI outputs critically and correct mappings.
• Comfortable with command-line tools and Git/GitHub.
• Proficiency in Python or SQL to inspect data and review AI-generated code.

Responsibilities

• Extend and maintain disease data models for manifestations, phenotypes, and biomarkers.
• Harmonize reference data sources and map to biomedical ontologies.
• Guide AI agents in curation tasks and improve prompts, templates, QC.
• Author and version data model artifacts in LinkML with GitHub.
• Register controlled vocabularies in enterprise terminology systems.
• Define validation rules and quality checks for harmonized data.
• Integrate disease models with adjacent data domains and support pipelines.
• Engage scientific SMEs to test model updates and ensure alignment.
• Write guidelines for future curation consistency.
• Report progress and decisions to client stakeholders.

Skills

Biomarker domain knowledge

Information modeling

LinkML

Python

SQL

Git/GitHub

AI tool usage

Command-line

Education

PhD in Life Sciences

MS with biomarker/clinical data

Tools

LinkML

GitHub

Python

SQL

Job description

Rancho BioSciences is seeking a biomedical data specialist to model, harmonize, and curate disease and biomarker data for pharma clients. You will scale AI-ready data products and contribute scientific judgment within an agent-assisted framework.

The role requires deep domain knowledge, strong information modeling, and proficiency with LinkML, Python/SQL, and GitHub. This is a fully remote, client-facing position in Europe.