{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/city/ca-client-field-office/"},"x-facet":{"type":"city","slug":"ca-client-field-office","display":"Ca Client Field Office","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_ef2f8267-7c3"},"title":"Machine Learning Data Specialist","description":"<p>We are seeking a Machine Learning Data Specialist to join our team. The ideal candidate will have a foundational understanding of machine learning, data annotation, quality assurance, and natural language processing. They will play a pivotal role in updating our machine learning models and ensuring their efficacy.</p>\n<p><strong>Main Tasks &amp; Responsibilities</strong></p>\n<ul>\n<li>Update training and test model databases with new or amended synthetic textual and image data.</li>\n<li>Modify and refine machine learning data creation, annotation, and rating guidelines.</li>\n<li>Initiate model training processes using internal tools and command-line interfaces.</li>\n<li>Evaluate the performance of trained models to gauge their efficacy and readiness for deployment.</li>\n<li>Design and develop test and training datasets as per the criteria provided by the project manager and other full-time employees.</li>\n<li>Handle data efficiently, ensuring its integrity throughout the workflow.</li>\n<li>Engage in data relevance tasks, ensuring data sets are aligned with project goals.</li>\n<li>Annotate data accurately, ensuring it adheres to set guidelines.</li>\n<li>Conduct manual quality analysis of model results.</li>\n<li>Recognize error patterns and report anomalies for further investigation.</li>\n<li>Deliver detailed reports on findings, including aspects such as utterance quality, LLM evaluation, ASR bug tracking, and customer pain points to be reviewed by the User Experience Research team.</li>\n<li>Implement basic quality control measures and ensure the reliability of processed data.</li>\n<li>Utilize intermediate data analysis techniques to extract insights and inform decision-making.</li>\n<li>Arbitrate discrepancies effectively, ensuring consistent data quality.</li>\n<li>Apply basic knowledge of natural language processing and linguistics to data processing tasks.</li>\n<li>Ensure linguistic accuracy in all processed and annotated data.</li>\n</ul>\n<p><strong>Requirements</strong></p>\n<ul>\n<li>Bachelor&#39;s degree in Computer Science, Data Science, Linguistics or Computational Linguistics or a related field.</li>\n<li>Ability to work in a fast-paced, collaborative environment.</li>\n<li>Excellent communication skills.</li>\n<li>Familiarity with command-line tools and interfaces.</li>\n<li>Strong analytical skills with the ability to identify patterns and anomalies.</li>\n</ul>\n<p><strong>Additional Information</strong></p>\n<ul>\n<li>This role primarily focuses on English US data sets; however, familiarity with translation or multi-lingual data sets can be a plus for future projects.</li>\n</ul>\n<p style=\"margin-top:24px;font-size:13px;color:#666;\">Job Data by <a href=\"https://yubhub.co\">YubHub</a>.</p>","url":"https://welocalize.wd1.myworkdayjobs.com/en-US/welocalize/job/CA-Client-Field-Office-San-Fran-Bay-Area/Data-Labeling-Associate_R0007638","directApply":true,"hiringOrganization":{"@type":"Organization","name":"WeLocalize","sameAs":"https://www.welocalize.com","logo":"https://logos.yubhub.co/welocalize.com.png"},"x-apply-url":"https://welocalize.wd1.myworkdayjobs.com/en-US/welocalize/job/CA-Client-Field-Office-San-Fran-Bay-Area/Data-Labeling-Associate_R0007638","x-work-arrangement":null,"x-experience-level":null,"x-job-type":"full-time","x-salary-range":null,"x-skills-required":["machine learning","data annotation","quality assurance","natural language processing","command-line tools","data analysis"],"x-skills-preferred":["translation","multi-lingual data sets"],"x-benefits":[],"x-licences":[],"x-visa-sponsorship":"unknown","x-visa-sponsorship-text":null,"x-work-authorisation":"unknown","x-work-authorisation-text":null,"datePosted":"2026-09-09T00:00:00.000Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"CA Client Field Office (San Fran Bay Area)"}},"employmentType":"FULL_TIME","occupationalCategory":"Data Science","industry":"Technology","skills":"machine learning, data annotation, quality assurance, natural language processing, command-line tools, data analysis, translation, multi-lingual data sets"}]}