Rwd Analytics Engineer

At Roche you can show up as yourself, embraced for the unique qualities you bring.Our culture encourages personal expression, open dialogue, and genuine connections, where you are valued, accepted and respected for who you are, allowing you to thrive both personally and professionally.This is how we aim to prevent, stop and cure diseases and ensure everyone has access to healthcare today and for generations to come.Join Roche, where every voice matters.The PositionMISSIONAs a Real World Data (RWD) Analytics Engineer, you will be part of a medical informatics team working with data scientists to understand their analytics needs and translate this into scalable and reusable data pipelines.Responsibilities include mapping data to/from RWD common data models such as OMOP and FHIR and ensuring quality of data is retained throughout the process.You will also work with IT teams to design and develop solutions for more declarative and reusable approaches to mapping data between data models.What You’ll Be Working OnYou will be supporting projects that require harmonization of source data models to/from common data models such as OMOP or FHIR.Occasionally, this may include custom data models, depending on product/project needs.You will be collaborating with clinical terminologists, medical informatics architects, data engineers, and data scientists to produce data sets that are ready for analysis or model building.You will also be responsible for creating and applying tests to the data pipeline using state of the art approaches, ensuring that the mapped data retain the same semantics as the original data within the context of specific use cases.In addition to supporting specific projects with analytics engineering needs, you will also leverage this experience to help design and develop scalable ways for mapping data.ResponsibilitiesSyntactically and semantically map data to/from RWD common data models (e.g., OMOP, FHIR) using dbt or similar toolsDesign, develop, and test ETL/ELT pipelines for real world dataProvide complete documentation and communication of all processes, methods, and resultsIntegrate vocabularies/terminologies using REST APIs and/or via relational tablesCo-create scalable approaches for mapping data using declarative and functional programming approachesSTAKEHOLDER MANAGEMENT AND PARTNERINGUnderstand the complexities of RWD use cases from both business and IT/technical perspectives and develop a strategic approach to balance short-term benefits and long-term costsContribute and share learnings throughout RWD communities, particularly product teams looking to leverage RWDAct as a strategic partner to business and research stakeholders, translating complex clinical objectives into actionable, high-quality data product requirementsPartner with IT business domain leadership to influence product roadmapsServe as an ambassador of medical informatics and the highlight the importance of clinical terminology management to business stakeholders, IT business domains, and senior leadershipQualificationsBachelor’s or Master’s degree in computer science, data science, informaticsHands-on experience with healthcare dataIn at least one of the following disease areas: oncology, neuro, immunology, infectious diseases, ophthalmology, cardiovascular and metabolismHands-on experience with real world data, specifically OMOPExperience with terminology integration, including OHDSI Athena and UMLSExperience with LLMs or NLP frameworks for extracting structured data from unstructured clinical text (e.g., electronic health records, clinical notes) to feed into OMOP/FHIR modelsFamiliarity with context-aware AI tools, such as the Model Context Protocol (MCP), and experience in prompt engineering for data discovery or code generation tasksExperience with AI-augmented data quality tools or ML-based anomaly detection for monitoring data pipelines and identifying semantic drift in mapped dataHands-on experience with relational databases and cloud platforms such as Snowflake(Preferred) Experience with graph databases such as Neo4j and GraphQL(Preferred) Experience with SDTMSQL, Python (numpy, pandas, etc.) or RStrong software engineering background including test driven development, object oriented programming, functional programming, CI/CD, gitExcellent verbal and written communication skills in EnglishExperience working with IT/technical development teams and able to translate between business needs and technical requirementsAbility to work with minimal supervision, exercising discretion and independent judgmentAbility to build collaboration and positive relationships in an agile, matrixed, multinational organizationTravelMinimized by leveraging virtual collaboration methodsWho we areA healthier future drives us to innovate.Together, more than 100’000 employees across the globe are dedicated to advance science, ensuring everyone has access to healthcare today and for generations to come.Our efforts result in more than 26 million people treated with our medicines and over 30 billion tests conducted using our Diagnostics products.We empower each other to explore new possibilities, foster creativity, and keep our ambitions high, so we can deliver life-changing healthcare solutions that make a global impact.Let’s build a healthier future, together.Roche is an Equal Opportunity Employer.#J-*****-Ljbffr

Bachelor’s or Master’s degree in computer science, data science, informatics Hands-on experience with healthcare data In at least one of the following disease areas: oncology, neuro, immunology, infectious diseases, ophthalmology, cardiovascular and metabolism Hands-on experience with real world data, specifically OMOP Experience with terminology integration, including OHDSI Athena and UMLS Experience with LLMs or NLP frameworks for extracting structured data from unstructured clinical text (e.g., electronic health records, clinical notes) to feed into OMOP/FHIR models Familiarity with context-aware AI tools, such as the Model Context Protocol (MCP), and experience in prompt engineering for data discovery or code generation tasks Experience with AI-augmented data quality tools or ML-based anomaly detection for monitoring data pipelines and identifying semantic drift in mapped data Hands-on experience with relational databases and cloud platforms such as Snowflake (Preferred) Experience with graph databases such as Neo4j and GraphQL (Preferred) Experience with SDTM SQL, Python (numpy, pandas, etc.) or R Strong software engineering background including test driven development, object oriented programming, functional programming, CI/CD, git Excellent verbal and written communication skills in English Experience working with IT/technical development teams and able to translate between business needs and technical requirements Ability to work with minimal supervision, exercising discretion and independent judgment Ability to build collaboration and positive relationships in an agile, matrixed, multinational organization

A healthier future drives us to innovate. Together, more than 100’000 employees across the globe are dedicated to advance science, ensuring everyone has access to healthcare today and for generations to come. Our efforts result in more than 26 million people treated with our medicines and over 30 billion tests conducted using our Diagnostics products. We empower each other to explore new possibilities, foster creativity, and keep our ambitions high, so we can deliver life-changing healthcare solutions that make a global impact. Let’s build a healthier future, together. Roche is an Equal Opportunity Employer. #J-*****-Ljbffr