Research Engineer, Knowledge Systems

MindWalk Holdings Corp.; Diepenbeek; On-site; EUR 80,000 - 120,000; Full time

Job summary

MindWalk is a global biologics discovery company applying Bio-native AI, deep data, and advanced lab research to accelerate discovery of antibodies and related therapies.

We seek a hands-on Research Engineer to design how biological information flows from raw data to usable knowledge for scientists and AI agents, defining data domains, models, metadata, and access patterns while ensuring scalable, trustworthy information through ontology-driven architecture.

Qualifications

• Experience with data and information architecture in production.
• Experience designing metadata models, catalogs, or registries for findability and retrieval.
• Some working knowledge of RDF/OWL/SHACL or comparable knowledge-representation tools.
• Experience in biomedical, pharmaceutical, or another evidence-heavy scientific domain.
• An MSc or PhD in a relevant field, or equivalent experience.
• Good written and oral communication skills in English.

Responsibilities

• Architect data flows from raw biological data to usable systems.
• Define data domains, models, metadata, and access patterns.
• Develop metadata models and registries for findability and retrieval.
• Ensure data lineage, contracts, and storage trade-offs.
• Communicate effectively with scientists and AI agents.

Skills

Data architecture

Metadata modeling

English communication

Biomedical data domain experience

Documentation and data governance

Education

MSc or PhD in a relevant field

Tools

RDF/OWL/SHACL

LinkML

ROBOT

SSSOM

LangGraph

AWS

Model Context Protocol

Job description

Position

Europe

Research Engineer, Knowledge Systems

MindWalk is a global biologics discovery company integrating Bio-native AI, deep data, and advanced lab research to accelerate discovery and development of therapeutic, anti-drug and diagnostic antibodies, peptide-based therapies, vaccines and beyond. We deliver end-to-end solutions spanning target exploration, discovery, engineering, characterization, production, and humanization—available as full-service partnerships, existing asset co-development or modular SaaS access. We partner with leading biotech and pharmaceutical organizations, applying our unified biointelligence ecosystem to advance next-generation biologics that improve lives.

Job Description:

We're looking for a hands-on engineer to architect how biological information flows through MindWalk, from raw data to something scientists and AI agents can actually use. You'll define the data domains, models, metadata, and access patterns that turn scattered biological data into a coherent, navigable system.

Ontology and formal knowledge representation are part of the job, but the core of this role is information architecture: deciding how information is organized, versioned, cataloged, and served so it stays trustworthy as it scales.

Key responsibilities:

• Real production experience with data and information architecture: modeling, authoritative sources, lineage, contracts, and storage trade-offs.
• Experience designing metadata models, catalogs, or registries for findability and retrieval.
• Some working knowledge of RDF/OWL/SHACL or comparable knowledge-representation tools.
• Experience in biomedical, pharmaceutical, or another evidence-heavy scientific domain.
• An MSc or PhD in a relevant field, or equivalent experience.
• Good written and oral communication skills in English.

Requirements:

• Real production experience with data and information architecture: modeling, authoritative sources, lineage, contracts, and storage trade-offs.
• Experience designing metadata models, catalogs, or registries for findability and retrieval.
• Some working knowledge of RDF/OWL/SHACL or comparable knowledge-representation tools.
• Experience in biomedical, pharmaceutical, or another evidence-heavy scientific domain.
• An MSc or PhD in a relevant field, or equivalent experience.
• Good written and oral communication skills in English.

Strong candidates may also have:

• Ontology tooling such as LinkML, ROBOT, or SSSOM.
• Agent frameworks like LangGraph or Model Context Protocol, or hybrid graph/vector retrieval.
• AWS or other cloud-native deployment experience.
• Familiarity with FAIR data principles or regulated scientific environments.
• Working knowledge of Information Management domains like Master Data Management (MDM), Data Governance, and Data Security.