{"schemaVersion":"jobsearcher.job.v1","id":"b0ece4fa1c78182f5f1a9f06","url":"https://jobsearcher.com/jobs/b0ece4fa1c78182f5f1a9f06","canonicalUrl":"https://jobsearcher.com/jobs/b0ece4fa1c78182f5f1a9f06","title":"Data Engineer - Research (Remote)","description":"About the CompanyThe company specializes in photonics technology.About the RoleYou will build and maintain the analysis library and data infrastructure used to turn engineering test data into actionable insights. Working in a deep-tech R&D environment, you will develop Python-based tools and scalable data solutions that support characterization data analysis, storage, and traceability.Key ResponsibilitiesArchitect a Python library focused on pipeline orchestration for characterization data.Separate analysis logic from underlying file formats and storage schemas.Develop scalable solutions for local, remote, and distributed execution environments.Integrate dataframe logging and transformation lineage, including database export capabilities.Build multi-site infrastructure for test data and metadata storage.Develop ingestion mechanisms for relational database metadata updates.Standardize data retrieval and storage conventions to ensure end-to-end traceability.Required QualificationsMSc in Computer Science, Engineering, or a scientific discipline, or equivalent practical experience.At least 5 years of experience working with data in an R&D, research center, or instrument-heavy environment.Strong Python expertise, including experience designing libraries and APIs.Proficiency in SQL, Git, and UNIX/bash.Experience building and operating ETL/ELT pipelines with modern orchestrators in production.Familiarity with scientific data formats and structured data storage concepts.Strong written and spoken English skills.Work Arrangement & Employment Details100% workload.Up to two days per week of home office.Initial interim period of 3–6 months, followed by a permanent position.","company":"Torentify","rawCompany":"torentify","city":"Denver","state":"CO","isRemote":true,"isActive":false,"createdAt":"2026-11-13T09:16:15.834Z","occupations":[{"code":"15-1243.01","title":"Data Warehousing Specialists","slug":"data-warehousing-specialists"},{"code":"15-1252.00","title":"Software Developers","slug":"software-developers"},{"code":"15-2051.00","title":"Data Scientists","slug":"data-scientists"}],"industries":[{"code":"541715","title":"Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)","slug":"research-and-development-in-the-physical-engineering-and-life-sciences-except-nanotechnology-and-biotechnology"},{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Data Engineer - Research (Remote)","description":"About the CompanyThe company specializes in photonics technology.About the RoleYou will build and maintain the analysis library and data infrastructure used to turn engineering test data into actionable insights. Working in a deep-tech R&D environment, you will develop Python-based tools and scalable data solutions that support characterization data analysis, storage, and traceability.Key ResponsibilitiesArchitect a Python library focused on pipeline orchestration for characterization data.Separate analysis logic from underlying file formats and storage schemas.Develop scalable solutions for local, remote, and distributed execution environments.Integrate dataframe logging and transformation lineage, including database export capabilities.Build multi-site infrastructure for test data and metadata storage.Develop ingestion mechanisms for relational database metadata updates.Standardize data retrieval and storage conventions to ensure end-to-end traceability.Required QualificationsMSc in Computer Science, Engineering, or a scientific discipline, or equivalent practical experience.At least 5 years of experience working with data in an R&D, research center, or instrument-heavy environment.Strong Python expertise, including experience designing libraries and APIs.Proficiency in SQL, Git, and UNIX/bash.Experience building and operating ETL/ELT pipelines with modern orchestrators in production.Familiarity with scientific data formats and structured data storage concepts.Strong written and spoken English skills.Work Arrangement & Employment Details100% workload.Up to two days per week of home office.Initial interim period of 3–6 months, followed by a permanent position.","datePosted":"2026-11-13T09:16:15.834Z","dateModified":"2026-11-13T09:16:15.834Z","hiringOrganization":{"@type":"Organization","name":"Torentify","sameAs":"https://jobsearcher.com"},"jobLocationType":"TELECOMMUTE","applicantLocationRequirements":{"@type":"Country","name":"US"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Denver","addressRegion":"CO","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"b0ece4fa1c78182f5f1a9f06"},"url":"https://jobsearcher.com/jobs/b0ece4fa1c78182f5f1a9f06"}}