{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/data-pipeline-architecture"},"x-facet":{"type":"skill","slug":"data-pipeline-architecture","display":"Data Pipeline Architecture","count":2},"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_c7e58f60-5fa"},"title":"Software Engineer - Learning Engineering and Data (LEaD) Program","description":"<p>As a member of our Miami-based Learning Engineering and Data (LEaD) program, you will work alongside technology mentors and leaders to develop and maintain applications and tools spanning front-office, middle-office, and back-office functions in a dynamic and fast-paced environment.</p>\n<p>Our technology teams are looking for Software Engineers with C++, Python, or Java to design, implement, and maintain systems supporting our technology business functions.</p>\n<p>Candidate is expected to:</p>\n<ul>\n<li>Work closely with technology teams to develop requirements and specifications for varying projects</li>\n<li>Take part in the development and enhancement of the backend distributed system</li>\n<li>Apply AI/ML (deep learning, natural language processing, large language models) to practical and comprehensive technology solutions</li>\n</ul>\n<p>Qualifications/Skills Required:</p>\n<ul>\n<li>2-5 years of experience working with C++, Python, or Java</li>\n<li>Experience with ML libraries, Pandas, NumPy, FastAPI (Python), Boost (C++), Spring Boot (Java)</li>\n<li>Must be comfortable working in both Unix/Linux and Windows environments</li>\n<li>Good understanding of various design patterns</li>\n<li>Strong analytical and mathematical skills along with an interest/ability to quickly learn additional languages and quantitative concepts</li>\n<li>Solid communication skills</li>\n<li>Able to work collaboratively in a fast-paced environment with a passion to solving complex problems</li>\n<li>Detail oriented, organized, demonstrating thoroughness and strong ownership of work</li>\n</ul>\n<p>Desirable Skills/Knowledge:</p>\n<ul>\n<li>Bachelor or Master&#39;s degree in Computer Science, Applied Mathematics, Statistics, Data Science/ML/AI, or a related technical or engineering field</li>\n<li>Demonstrable passion for developing LLM-powered products whether that is through commercial experience or open source/academic projects you have worked on in your own time</li>\n<li>Hands-on experience building ML and data pipeline architectures</li>\n<li>Understanding of distributed messaging systems</li>\n<li>Experience with Docker/Kubernetes, microservices architecture in a cloud environment (AWS, GCP preferred)</li>\n<li>Experience with relational and non-relational database platforms</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_c7e58f60-5fa","directApply":true,"hiringOrganization":{"@type":"Organization","name":"IT LEad Program","sameAs":"https://mlp.eightfold.ai","logo":"https://logos.yubhub.co/mlp.eightfold.ai.png"},"x-apply-url":"https://mlp.eightfold.ai/careers/job/755953879362","x-work-arrangement":"onsite","x-experience-level":"mid","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["C++","Python","Java","ML libraries","Pandas","NumPy","FastAPI","Boost","Spring Boot"],"x-skills-preferred":["Bachelor or Master's degree in Computer Science, Applied Mathematics, Statistics, Data Science/ML/AI, or a related technical or engineering field","Demonstrable passion for developing LLM-powered products","Hands-on experience building ML and data pipeline architectures","Understanding of distributed messaging systems","Experience with Docker/Kubernetes, microservices architecture in a cloud environment (AWS, GCP preferred)","Experience with relational and non-relational database platforms"],"datePosted":"2026-04-18T22:13:11.242Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Miami, Florida, United States of America"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Finance","skills":"C++, Python, Java, ML libraries, Pandas, NumPy, FastAPI, Boost, Spring Boot, Bachelor or Master's degree in Computer Science, Applied Mathematics, Statistics, Data Science/ML/AI, or a related technical or engineering field, Demonstrable passion for developing LLM-powered products, Hands-on experience building ML and data pipeline architectures, Understanding of distributed messaging systems, Experience with Docker/Kubernetes, microservices architecture in a cloud environment (AWS, GCP preferred), Experience with relational and non-relational database platforms"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_c4cc3bc0-a5d"},"title":"Senior Analytics Engineer","description":"<p><strong>Job Title: Senior Analytics Engineer</strong></p>\n<p>You&#39;ll be part of a team that empowers you to do the best work of your life. As a Senior Analytics Engineer at ZoomInfo, you&#39;ll be responsible for building deep expertise in our company data pipeline architecture.</p>\n<p><strong>Key Responsibilities:</strong></p>\n<ul>\n<li>Master our company data pipeline architecture,how data flows from ingestion through profiling, what transforms are applied at each stage, and how components interconnect</li>\n<li>Read and analyze production code to understand data transformations, trace data lineage, and assess how proposed changes would impact the system</li>\n<li>Develop frameworks for evaluating tradeoffs between technical complexity, implementation effort, and customer impact</li>\n<li>Create clear documentation, system maps, and knowledge resources that capture architecture decisions, dependencies, and design rationale</li>\n</ul>\n<p><strong>What You&#39;ll Do:</strong></p>\n<p>In your first 6-12 months, your primary focus will be building deep expertise in our pipeline architecture and contributing to our infrastructure transition. You&#39;ll work alongside other analysts who have context on our systems, learning the architecture while bringing fresh perspectives and technical depth.</p>\n<p>As you gain mastery and systems stabilize, you&#39;ll increasingly own pipeline architecture decisions and lead strategic data improvement initiatives.</p>\n<p><strong>Requirements:</strong></p>\n<ul>\n<li>Bachelor&#39;s degree in Computer Science, Engineering, Mathematics, Statistics, or related quantitative field</li>\n<li>5+ years of experience in data analytics, data engineering, or related technical roles</li>\n<li>Experience working with data pipelines, ETL systems, or data processing infrastructure,you understand how data moves through systems and what can go wrong</li>\n<li>Ability to read and understand code (Python, Java, SQL, or similar) to analyze data transformations, understand system logic, and assess technical feasibility</li>\n<li>Strong programming skills in Python and SQL for data analysis and manipulation</li>\n<li>Experience solving ambiguous, multi-faceted data problems that required figuring out the approach, not just executing a well-defined analysis</li>\n<li>Demonstrated ability to work effectively with Engineering and/or Product teams, translating between technical implementation and business/customer needs</li>\n<li>Strong analytical skills with ability to investigate complex issues systematically</li>\n<li>Excellent communication skills,able to explain technical concepts clearly to diverse audiences</li>\n<li>Self-directed with strong ownership mentality,you drive your work forward and know when to seek input</li>\n</ul>\n<p><strong>Preferred Qualifications:</strong></p>\n<ul>\n<li>Experience with company data, business data, web data acquisition, or data quality initiatives</li>\n<li>Experience with data profiling, entity resolution, record linkage, or data matching systems</li>\n<li>Background contributing to</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_c4cc3bc0-a5d","directApply":true,"hiringOrganization":{"@type":"Organization","name":"ZoomInfo","sameAs":"https://www.zoominfo.com/","logo":"https://logos.yubhub.co/zoominfo.com.png"},"x-apply-url":"https://job-boards.greenhouse.io/zoominfo/jobs/8408633002","x-work-arrangement":"onsite","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["data pipeline architecture","data transformation","ETL systems","data processing infrastructure","Python","SQL","data analysis","data manipulation","ambiguous data problems","data quality initiatives"],"x-skills-preferred":[],"datePosted":"2026-04-18T15:44:11.964Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Vancouver, Washington, United States; Waltham, Massachusetts, United States"}},"employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"data pipeline architecture, data transformation, ETL systems, data processing infrastructure, Python, SQL, data analysis, data manipulation, ambiguous data problems, data quality initiatives"}]}