{"schemaVersion":"jobsearcher.job.v1","id":"5d6d54c19ab5a23d67db0f87","url":"https://jobsearcher.com/jobs/5d6d54c19ab5a23d67db0f87","canonicalUrl":"https://jobsearcher.com/jobs/5d6d54c19ab5a23d67db0f87","title":"Data Engineer","description":"About The RoleYou will engineer the critical path of CYBERIA's Data Platform — ingestion, transformation, feature pipelines, and vector retrieval — with SLOs for latency, freshness, and quality.ResponsibilitiesBuild and operate batch and streaming pipelines with offline + online parityImplement feature stores with sub-50 ms p99 reads and point-in-time correctnessDevelop pipeline designers that turn documents (PDF, DOCX) into structured, AI-ready dataInstrument everything: lineage, data quality checks, and cost telemetry by defaultHarden prototypes from applied ML teams into production-grade platform featuresRequirements4+ years engineering production data systemsStrong Python plus SQL; experience with Spark, dbt, Airflow/Dagster, or similarFamiliarity with vector databases, embeddings, or retrieval systems a strong plusComfort with distributed systems, observability, and on-callBenefitsFully remote within the USCompetitive base + equityLearning and conference budgetPremium health benefits and 401(k) match","company":"Cyberia Software","rawCompany":"cyberia software","city":"Denver","state":"CO","isRemote":false,"isActive":false,"createdAt":"2026-09-12T08:38:00.548Z","occupations":[{"code":"15-1243.01","title":"Data Warehousing Specialists","slug":"data-warehousing-specialists"},{"code":"15-2051.00","title":"Data Scientists","slug":"data-scientists"},{"code":"15-1243.00","title":"Database Architects","slug":"database-architects"}],"industries":[{"code":"541512","title":"Computer Systems Design Services","slug":"computer-systems-design-services"},{"code":"518210","title":"Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services","slug":"computing-infrastructure-providers-data-processing-web-hosting-and-related-services"},{"code":"541511","title":"Custom Computer Programming Services","slug":"custom-computer-programming-services"}],"jobPosting":{"@context":"https://schema.org","@type":"JobPosting","title":"Data Engineer","description":"About The RoleYou will engineer the critical path of CYBERIA's Data Platform — ingestion, transformation, feature pipelines, and vector retrieval — with SLOs for latency, freshness, and quality.ResponsibilitiesBuild and operate batch and streaming pipelines with offline + online parityImplement feature stores with sub-50 ms p99 reads and point-in-time correctnessDevelop pipeline designers that turn documents (PDF, DOCX) into structured, AI-ready dataInstrument everything: lineage, data quality checks, and cost telemetry by defaultHarden prototypes from applied ML teams into production-grade platform featuresRequirements4+ years engineering production data systemsStrong Python plus SQL; experience with Spark, dbt, Airflow/Dagster, or similarFamiliarity with vector databases, embeddings, or retrieval systems a strong plusComfort with distributed systems, observability, and on-callBenefitsFully remote within the USCompetitive base + equityLearning and conference budgetPremium health benefits and 401(k) match","datePosted":"2026-09-12T08:38:00.548Z","dateModified":"2026-09-12T08:38:00.548Z","hiringOrganization":{"@type":"Organization","name":"Cyberia Software","sameAs":"https://jobsearcher.com"},"jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Denver","addressRegion":"CO","addressCountry":"US"}},"identifier":{"@type":"PropertyValue","name":"JobSearcher","value":"5d6d54c19ab5a23d67db0f87"},"url":"https://jobsearcher.com/jobs/5d6d54c19ab5a23d67db0f87"}}