Senior Scientific Knowledge Engineer

GSK•Upper Providence, PA

About The Position

Purpose of Onyx The Onyx Research Data Tech organization is GSK’s Research data ecosystem which has the capability to bring together, analyze, and power the exploration of data at scale. We partner with scientists across GSK to define and understand their challenges and develop tailored solutions that meet their needs. The goal is to ensure scientists have the right data and insights when they need it to give them a better starting point for and accelerate medical discovery. Ultimately, this helps us get ahead of disease in more predictive and powerful ways. Onyx is a full-stack shop consisting of product and portfolio leadership, data engineering, infrastructure and DevOps, data / metadata / knowledge platforms, and AI/ML and analysis platforms, all geared toward: Building a next-generation, metadata- and automation-driven data experience for GSK’s scientists, engineers, and decision-makers, increasing productivity and reducing time spent on “data mechanics” Providing best-in-class AI/ML and data analysis environments to accelerate our predictive capabilities and attract top-tier talent Aggressively engineering our data at scale, as one unified asset, to unlock the value of our unique collection of data and predictions in real-time The Scientific Knowledge Engineering team, which sits within the Onyx Product Management organization, is responsible for the data modeling, ontology definition and management, vocabulary mapping, and other key metadata activities that ensure Onyx platforms and data assets speak scientific language. They are a core factor in delivering the GSK R&D Knowledge Graph – the semantic layer that connects all of our data and metadata systems – as well as the core metadata experiences that ultimately allow us to build products and services that both delight our customers and enable impressive automation and intelligence. This role is responsible for maximizing the value of our data assets over a lifetime to bring purpose to data by acting as translators of highly technical information from domain experts into an appropriate data model – complete with significant ontology and vocabulary - that can be utilized to effectively structure and index the data. Specifically working with Product managers and R&D subject matter expertise to define the language (data models, ontology, standards, etc.) of science into data products by acting as the voice of “Knowledgebase” and interoperability/value of asset. This includes responsibility for the understanding and translation of computational methods back through the data chain to maximize the quality and speed of data from source to drive experimental multi-variant analysis and data driven decision-making teams to ensure that we have the right infrastructure components to power our platforms and services reliably and securely.

Requirements

Masters degree in Bioinformatics, Biomedical Science, Biomedical Engineering, Molecular Biology, or Computer Science (with a life science application focus)
6+ years of relevant work experience
Experience contributing to Knowledge Graph development efforts, including entity modeling, relationship design, and schema governance
Experience in operating and leading across organizational boundaries a matrixed team
Experience with industry standard data management / metadata platforms e.g. Collibra, Datahub, Datum, Informatica
Proficiency in at least one programming language — preferably Python — for scripting vocabulary mappings, building data models, automating QC, and prototyping pipelines
Experience with bioinformatics pipelines and workflow management systems (e.g., Nextflow,)

Nice To Haves

Membership of industry committee, board, consortium, or data standards group
Participation in peer-reviewed research (both publication and review), particularly in genetics and/or bioinformatics
Experience with data governance and data quality tooling (e.g., Ataccama, Informatica, Talend, OpenRefine, Great Expectations, dbt)
Experience with industry standard tools for building data protocols e.g. Avro, Protocol Buffers, Thrift
Experience with at least one programming language – e.g. Python – for scripting vocabulary mappings, building data models, etc
Experience supporting LLM integration or AI-readiness workflows — including metadata enrichment, entity linking, embedding pipelines, or retrieval-augmented generation (RAG) architectures
Understanding of vector databases and their role in semantic search and knowledge retrieval (e.g., Weaviate, Chroma)
Familiarity with cloud data platforms and infrastructure relevant to large-scale biological data (e.g., AWS, GCP, Azure)
Familiarity with graph database technologies (e.g., Neo4j, Amazon Neptune, Stardog, GraphDB, TigerGraph)
Experience designing or contributing to FAIR data frameworks, data catalogs, or self-service data enablement initiatives
Hands-on experience with open-source ontology tools and languages: Protégé, SPARQL, OWL, SKOS, SHACL, RML, RDF/Turtle
Working knowledge of major life sciences ontologies: Gene Ontology (GO), OBO Foundry ontologies (CL, UBERON, HPO, MONDO, CHEBI, EFO, CLO), MeSH, SNOMED CT, UMLS
Experience with CDISC standards (SDTM, ADaM, SEND) or other clinical/research data standards relevant to pharmaceutical R&D
Familiarity with linked data principles and semantic web technologies
Experience with multi-omics data formats and standards (e.g., h5ad/AnnData, VCF, FASTQ, MAF, CellXGene, GEO)
Experience with industry-standard tools for building data serialization protocols (e.g., JSON Schema, LinkML)

Responsibilities

Definition of schemas and data models of scientific information required for the creation of value adding data products. This includes accountability for the quality control and mapping specifications to be industrialized by data engineering and maintained in platform provisioned tooling.
Accountable for the quality control (through validation and verification) of mapping specifications to be industrialized by data engineering and maintained in platform provisioned tooling – e.g., models, schemas, controlled vocab.
Working with Product managers/engineers confidently convert business need into defined deliverable business requirements to enable the integration of large-scale biology data to predict, model, and stabilize therapeutically relevant protein complex and antigen conformations for drug and vaccine discovery.
Collaborate with external groups to align GSK data standards with industry/ academic ontologies ensuring that data standards are defined with usage/analytics in mind. They may also provide data source profiling and advisory consultancy to R&D outside of Onyx.
Support effective ingestion of data by GSK through understanding the entry requirements required by platform engineering teams and ensuring that the “barrier for entry” is met e.g. Scientific information has the appropriate metadata to be indexed, structured, integrated and standardised as needed. This may require articulation of GSK engineering standards and metadata information needs to third parties to ensure efficient and automate ingestion at scale.
Provides bespoke subject matter expertise for R&D data to translate deep science into data for actionable insights
Champion data lineage, data quality, and FAIR data principles across the Onyx platform, working with engineering and product teams to embed governance and quality frameworks into data pipelines
Contribute to and maintain documentation of data standards, ontology decisions, and mapping rationale to support organizational knowledge transfer and auditability
Support self-service data enablement by ensuring metadata and knowledge products are accessible, well-documented, and usable by scientists and analysts without requiring bespoke engineering support