Semantic Data Integrator
South San Francisco, CA

Job Description

Roche has been taken a strategic effort across functions and sites to improve data quality and to make data FAIR (findable, accessible, interoperable and reusable). We are a team of scientists, knowledge engineers, data curators and informaticians driving the development of standards and their roll-out in the Research and Development organization. Roche is leading this field due to the development of a variety of capabilities and processes underpinning the implementation of the FAIR principles. We are looking for a new team member to help us to enhance our semantic platform for terminology and metadata management. The enhancements will include extensions of the semantic model and the regular processing of various semantic key resources for content enrichment of the terminologies. These resources are used to support a variety of use cases such as data capture, data curation, text mining or semantic search. In your role you will support the Data Harmonization Service team to extend the range and the coverage of data standards across the Roche organization.

In this role you will:

* Collaborate with the Data Harmonization Service team to shape the further development and integration of our terminology and metadata management platform into the Roche landscape of FAIR data and services.


* Implement and constantly improve the acquisition and integration of major public terminological resources.


* Interface with teams working on semantic technologies to build a Roche knowledge graph with FAIR data.


* Engage with key customers of the Data Harmonization Service to supply high-quality and current terminologies using standards for knowledge representation and the content.


* Support the automation of terminology processing pipelines and implement intelligent processes for QA.


* Participate in pre-competitive initiatives to drive the implementation of FAIR data in the pharma industry.



We are looking for a motivated candidate with a passion for solving complex knowledge engineering and processing tasks to join a multi-cultural team working on leading innovative approaches in a science-driven industry. You have a background in Biology, Computer Science, Bioinformatics, Medical Informatics or related degree programs (MSc or PhD) and a good understanding in at least one of the following domains: biology, medicine or chemistry. Additionally, you bring:

* Excellent understanding of the Semantic Technology stack including triple stores, graph databases and semantic frameworks (eg JENA, RDF4J).


* Working experience with ontology tools like Topbraid Composer or Protégé and strong capability to write SPARQL queries


* Very good programming skills in JAVA and Python. R would be nice but not a prerequisite.


* Deep knowledge about RDF, RDFS, OWL and related vocabularies for knowledge representation such as SKOS, SKOS-XL, Dublin Core, PROV-O. Familiarity with REST APIs, their usage, e.g. via CURL, as well as with JSON.


* Good understanding of data and information architecture.


* Good knowledge about key semantic resources in the life sciences and data standards would be welcome, including some of the following : Ontology Lookup Service, Bioportal, NCIt, ICD-10, MedDRA, SNOMED, CDISC, Allotrope, OHDSI etc.


* You are a structured thinker with excellent analytical skills.


* You are goal oriented, a pro-active knowledge sharer and team player, and you are able to work independently on assigned tasks.


* Fluency in English



Working location either Basel, Switzerland, or South San Francisco, USA.

Roche is an equal opportunity employer.

Research & Development, Research & Development > Biometrics