{"version":"0.1","company":{"name":"YubHub","url":"https://yubhub.co","jobsUrl":"https://yubhub.co/jobs/skill/ml-model-serving"},"x-facet":{"type":"skill","slug":"ml-model-serving","display":"ML model serving","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_9aa7a5d2-3bd"},"title":"Senior AI Engineer","description":"<p>We&#39;re looking for a Senior AI Engineer who is obsessed with building AI systems that actually work in production: reliable, observable, cost-efficient, and genuinely useful. This is not a research role. You will ship AI-powered features that process real financial data for real businesses.</p>\n<p>LLM &amp; AI Pipeline Engineering</p>\n<ul>\n<li>Design, build, and maintain production-grade LLM integration pipelines , including retrieval-augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.</li>\n<li>Develop and operate AI features within Jeeves&#39;s core financial products: spend categorization, document extraction, anomaly detection, financial Q&amp;A, and automated reconciliation.</li>\n<li>Implement structured output validation, fallback handling, and confidence scoring to ensure AI decisions meet reliability standards for financial use cases.</li>\n</ul>\n<p>Retrieval &amp; Vector Search</p>\n<ul>\n<li>Design and maintain vector search pipelines using databases such as Pinecone, Weaviate, or pgvector to power semantic search and RAG-based features.</li>\n<li>Build document ingestion and chunking pipelines for Jeeves&#39;s financial data , processing invoices, receipts, policy documents, and transaction records.</li>\n</ul>\n<p>ML Model Serving &amp; Operations</p>\n<ul>\n<li>Collaborate with data scientists to take trained ML models from experimental notebooks to production serving infrastructure.</li>\n<li>Build and maintain model serving endpoints with appropriate latency SLOs, input validation, and output monitoring.</li>\n</ul>\n<p>Backend Integration &amp; Reliability</p>\n<ul>\n<li>Integrate AI services cleanly with Jeeves&#39;s backend microservices , designing clear API contracts, circuit breakers, and graceful degradation patterns.</li>\n<li>Write high-quality, testable backend code in Python or Go/Node.js to power AI-integrated features.</li>\n</ul>\n<p>Collaboration &amp; Growth</p>\n<ul>\n<li>Partner with Product, Backend Engineering, and Data Science to define the AI roadmap and translate requirements into reliable systems.</li>\n<li>Contribute to a culture of quality by writing design docs, reviewing peers&#39; AI system designs, and sharing learnings openly.</li>\n<li>Help grow the AI engineering practice at Jeeves by establishing patterns, tooling, and best practices that the broader team can build on.</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_9aa7a5d2-3bd","directApply":true,"hiringOrganization":{"@type":"Organization","name":"Jeeves","sameAs":"https://www.jeeves.com/","logo":"https://logos.yubhub.co/jeeves.com.png"},"x-apply-url":"https://jobs.lever.co/tryjeeves/03f901fc-7a43-4fae-9916-3b287a4bdff6","x-work-arrangement":"remote","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["Python","LLM","RAG","Pinecone","Weaviate","pgvector","ML model serving","backend engineering","API design","circuit breakers","graceful degradation","Go","Node.js"],"x-skills-preferred":[],"datePosted":"2026-04-17T12:38:17.504Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Mexico"}},"jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Finance","skills":"Python, LLM, RAG, Pinecone, Weaviate, pgvector, ML model serving, backend engineering, API design, circuit breakers, graceful degradation, Go, Node.js"}]}