{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/platform-reliability"},"x-facet":{"type":"skill","slug":"platform-reliability","display":"Platform Reliability","count":1},"x-feed-size-limit":100,"x-feed-sort":"enriched_at desc","x-feed-notice":"This feed contains at most 100 jobs (the most recently enriched). For the full corpus, use the paginated /stats/by-facet endpoint or /search.","x-generator":"yubhub-xml-generator","x-rights":"Free to redistribute with attribution: \"Data by YubHub (https://yubhub.co)\"","x-schema":"Each entry in `jobs` follows https://schema.org/JobPosting. YubHub-native raw fields carry `x-` prefix.","jobs":[{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_a57339aa-939"},"title":"Staff Data Engineer, tvScientific","description":"<p>We&#39;re seeking a Staff Data Engineer to lead the design, implementation, and evolution of our identity services and data governance platform. This role is critical to ensuring trusted, privacy-safe, and well-governed data across the organization.</p>\n<p>You will work at the intersection of data engineering, identity resolution, privacy, and platform reliability. This is an individual contributor role, where you will work to define and implement a strategic vision for data engineering within the organization.</p>\n<p>Responsibilities:</p>\n<ul>\n<li>Design and maintain a scalable identity resolution platform</li>\n<li>Build pipelines and services to ingest, normalize, link, and version identity data across multiple sources</li>\n<li>Ensure deterministic and probabilistic matching logic that is transparent, auditable, and measurable</li>\n<li>Partner with product and analytics teams to expose identity data through reliable, well-documented APIs and datasets</li>\n<li>Build and operate batch and streaming pipelines using modern data stack tools</li>\n<li>Create clear documentation, standards, and runbooks for identity and governance systems</li>\n<li>Own data governance foundations including data lineage, quality checks, schema enforcement, and access controls</li>\n<li>Implement privacy-by-design principles (PII handling, consent enforcement, retention policies)</li>\n<li>Collaborate with legal, privacy, and security teams to operationalize regulatory requirements (e.g., GDPR, CCPA)</li>\n<li>Establish monitoring and alerting for data quality, freshness, and integrity</li>\n</ul>\n<p>What we&#39;re looking for:</p>\n<ul>\n<li>Production data engineering experience</li>\n<li>Bachelor’s degree in computer science, related field or equivalent experience</li>\n<li>Proficiency in Spark and Scala, with proven experience building data infrastructure in Spark using Scala</li>\n<li>Experience in delivering significant technical initiatives and building reliable, large scale services</li>\n<li>Experience in delivering APIs backed by relationship-heavy datasets</li>\n<li>Experience implementing data governance practices, including data quality, metadata management, and access controls</li>\n<li>Strong understanding of privacy-by-design principles and handling of sensitive or regulated data</li>\n<li>Familiarity with data lakes, cloud warehouses, and storage formats</li>\n<li>Strong proficiency in AWS services</li>\n<li>Excellent written and verbal communication skills</li>\n<li>Successful design and implementation of scalable and efficient data infrastructure</li>\n<li>High attention to detail in implementation of automated data quality checks</li>\n<li>Effective collaboration with cross-functional teams</li>\n<li>Demonstrated ability to use AI to improve speed and quality in your day-to-day workflow for relevant outputs</li>\n<li>Strong track record of critical evaluation and verification of AI-assisted work (e.g., testing, source-checking, data validation, peer review)</li>\n<li>High integrity and ownership: you protect sensitive data, avoid over-reliance on AI, and remain accountable for final decisions and deliverables</li>\n</ul>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">XML job scraping automation by <a href=\"https://yubhub.co\">YubHub</a></p>","url":"https://yubhub.co/jobs/job_a57339aa-939","directApply":true,"hiringOrganization":{"@type":"Organization","name":"tvScientific","sameAs":"https://www.tvscientific.com/","logo":"https://logos.yubhub.co/tvscientific.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/pinterest/jobs/7642253","x-work-arrangement":"remote","x-experience-level":"staff","x-job-type":"full-time","x-salary-range":"$177,185-$364,795 USD","x-skills-required":["Spark","Scala","Data Engineering","Identity Resolution","Privacy","Platform Reliability","Data Governance","Data Lineage","Quality Checks","Schema Enforcement","Access Controls","AWS Services"],"x-skills-preferred":[],"datePosted":"2026-04-18T15:53:33.855Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"San Francisco, CA, US; Remote, US"}},"jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Spark, Scala, Data Engineering, Identity Resolution, Privacy, Platform Reliability, Data Governance, Data Lineage, Quality Checks, Schema Enforcement, Access Controls, AWS Services","baseSalary":{"@type":"MonetaryAmount","currency":"USD","value":{"@type":"QuantitativeValue","minValue":177185,"maxValue":364795,"unitText":"YEAR"}}}]}