We'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.
\nLLM & AI Pipeline Engineering - Design, build, and maintain production-grade LLM integration pipelines , including retrieval-augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.
\nDevelop and operate AI features within Jeeves's core financial products: spend categorization, document extraction, anomaly detection, financial Q&A, and automated reconciliation.
\nImplement structured output validation, fallback handling, and confidence scoring to ensure AI decisions meet reliability standards for financial use cases.
\nEvaluate and integrate AI frameworks and tools (LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases) and advocate for the right tool for the job.
\nEstablish prompt versioning and evaluation practices to ensure AI outputs remain accurate and consistent as models and data evolve.
\nRetrieval & Vector Search - Design and maintain vector search pipelines using databases such as Pinecone, Weaviate, or pgvector to power semantic search and RAG-based features.
\nBuild document ingestion and chunking pipelines for Jeeves's financial data , processing invoices, receipts, policy documents, and transaction records.
\nOptimize retrieval quality through embedding model selection, chunk strategy, metadata filtering, and re-ranking techniques.
\nML Model Serving & Operations - Collaborate with data scientists to take trained ML models from experimental notebooks to production serving infrastructure.
\nBuild and maintain model serving endpoints with appropriate latency SLOs, input validation, and output monitoring.
\nImplement model performance monitoring and data drift detection to ensure production models remain accurate over time.
\nSupport model retraining workflows by designing clean data pipelines and feature engineering that can be continuously updated.
\nBackend Integration & Reliability - Integrate AI services cleanly with Jeeves's backend microservices , designing clear API contracts, circuit breakers, and graceful degradation patterns.
\nWrite high-quality, testable backend code in Python or Go/Node.js to power AI-integrated features.
\nInstrument AI components with structured logging, distributed tracing, latency dashboards, and alerting to ensure operational visibility.
\nBuild human-in-the-loop review workflows for AI decisions that require oversight , particularly for high-value financial actions.
\nCollaboration & Growth - Partner with Product, Backend Engineering, and Data Science to define the AI roadmap and translate requirements into reliable systems.
\nContribute to a culture of quality by writing design docs, reviewing peers' AI system designs, and sharing learnings openly.
\nHelp grow the AI engineering practice at Jeeves by establishing patterns, tooling, and best practices that the broader team can build on.
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_5579e8fb-227","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/2f00206f-6091-4eed-8b5f-1325afdbfe30","x-work-arrangement":"remote","x-experience-level":"senior","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["LLM pipeline engineering","RAG architecture","ML system operation","Python programming","AI orchestration framework","ML model serving infrastructure","Observability tooling"],"x-skills-preferred":["Fintech experience","Prompt evaluation frameworks","ML lifecycle management tools","Real-time data streaming"],"datePosted":"2026-04-17T12:38:27.085Z","jobLocation":{"@type":"Place","address":{"@type":"PostalAddress","addressLocality":"Brazil"}},"jobLocationType":"TELECOMMUTE","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Finance","skills":"LLM pipeline engineering, RAG architecture, ML system operation, Python programming, AI orchestration framework, ML model serving infrastructure, Observability tooling, Fintech experience, Prompt evaluation frameworks, ML lifecycle management tools, Real-time data streaming"},{"@context":"https://schema.org","@type":"JobPosting","identifier":{"@type":"PropertyValue","name":"YubHub","value":"job_87a3f2e9-4c1"},"title":"Backend AI Engineer","description":"About the Role
\nWe are looking for a Backend AI Engineer to join our team and help build and scale backend systems that power AI Agents for the gaming industry, handling millions of customer support tickets at scale.
\nIn this role, you will work on high-throughput backend services, AI-powered workflows, and retrieval-based systems that support large-scale customer support automation. You will collaborate closely with AI Engineers, ML Engineers, and Product teams to design, build, deploy, and operate reliable backend systems that integrate AI components such as RAG pipelines and AI Agent orchestration.
\nThis is an excellent opportunity to work on production-grade AI systems operating at massive scale, where performance, reliability, and observability are critical.
\nWhat You’ll Do:
\nRequirements
\nGood to Have / Plus Skills
\nBonus Points
\nBenefits
\nXML job scraping automation by YubHub
","url":"https://yubhub.co/jobs/job_87a3f2e9-4c1","directApply":true,"hiringOrganization":{"@type":"Organization","name":"AI engineering team","sameAs":"https://apply.workable.com","logo":"https://logos.yubhub.co/j.com.png"},"x-apply-url":"https://apply.workable.com/j/C06078D2BC","x-work-arrangement":"hybrid","x-experience-level":"mid","x-job-type":"full-time","x-salary-range":null,"x-skills-required":["Python","FastAPI","MongoDB","YugabyteDB","PostgreSQL","Docker","Kubernetes","AWS","GCP","CI/CD","Grafana","Elasticsearch","Kibana","RAG"],"x-skills-preferred":["Jenkins","MCP","AI orchestration frameworks","AI/LLM-based systems","embeddings","vector search","Clojure","Gaming industry","Customer Support domain"],"datePosted":"2026-03-09T10:49:20.789Z","employmentType":"FULL_TIME","occupationalCategory":"Engineering","industry":"Technology","skills":"Python, FastAPI, MongoDB, YugabyteDB, PostgreSQL, Docker, Kubernetes, AWS, GCP, CI/CD, Grafana, Elasticsearch, Kibana, RAG, Jenkins, MCP, AI orchestration frameworks, AI/LLM-based systems, embeddings, vector search, Clojure, Gaming industry, Customer Support domain"}]}