Senior AI Engineer

<div><a href="https://himalayas.app/companies/jeeves">Jeeves</a> is a groundbreaking financial operating system built for global businesses that provides corporate cards, cross-border payments, and spend management software within one unified platform. The company operates across 20+ countries including Brazil, Canada, Colombia, Mexico, the United Kingdom, across Europe, and the United States, and serves over 5,000 clients ranging from venture-backed startups to SMBs around the world. With a mission to empower businesses with more efficient and cost-effective financial solutions worldwide, <a href="https://himalayas.app/companies/jeeves">Jeeves</a> combines cutting-edge financial technology with exceptional team expertise to transform the business financial landscape. <a href="https://himalayas.app/companies/jeeves">Jeeves</a> has been recognized as one of The Information's 50 Most Promising Startups in 2023, as well as a Y Combinator Top Company 2021-2023 and won "Fintech of the Year" at the European Fintech Awards.</div><div>Since graduating from Y Combinator in 2020, <a href="https://himalayas.app/companies/jeeves">Jeeves</a> has successfully raised over $380 million and is backed by top world-class investors including Andreessen Horowitz, Y Combinator, CRV, Tencent, Stanford University, Clocktower Ventures, and founders of more than 15 unicorns including David Velez (Nubank), Carlos Garcia (Kavak) and Sebastián Mejía (Rappi).</div><div><p><a href="https://himalayas.app/companies/jeeves">Jeeves</a> is building AI into the core of its financial platform — from intelligent spend categorization and anomaly detection to LLM-powered workflows that help finance teams move faster. 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.</p><p>This is not a research role. You will ship AI-powered features that process real financial data for real businesses. You'll work alongside backend engineers, data scientists, and product teams to take AI from prototype to production — and you'll help define how <a href="https://himalayas.app/companies/jeeves">Jeeves</a> builds with AI as the company scales.</p><p>If you've built LLM pipelines, designed RAG architectures, operated ML systems in production, and care deeply about what happens when your AI makes a wrong call in a financial context — we want to meet you.</p><div data-qa="job-description"><div><strong>Location</strong>: This is a full-time remote position. </div></div><h3>What You'll Do:</h3><ul><div><h3>LLM &amp; AI Pipeline Engineering</h3><li><p>Design, build, and maintain production-grade LLM integration pipelines — including retrieval-augmented generation (RAG), prompt engineering, output parsing, and chain orchestration.</p></li><li><p>Develop and operate AI features within <a href="https://himalayas.app/companies/jeeves">Jeeves</a>'s core financial products: spend categorization, document extraction, anomaly detection, financial Q&amp;A, and automated reconciliation.</p></li><li><p>Implement structured output validation, fallback handling, and confidence scoring to ensure AI decisions meet reliability standards for financial use cases.</p></li><li><p>Evaluate and integrate AI frameworks and tools (LangChain, LlamaIndex, OpenAI API, Anthropic API, HuggingFace, vector databases) and advocate for the right tool for the job.</p></li><li><p>Establish prompt versioning and evaluation practices to ensure AI outputs remain accurate and consistent as models and data evolve.</p></li><h3>Retrieval &amp; Vector Search</h3><li><p>Design and maintain vector search pipelines using databases such as Pinecone, Weaviate, or pgvector to power semantic search and RAG-based features.</p></li><li><p>Build document ingestion and chunking pipelines for <a href="https://himalayas.app/companies/jeeves">Jeeves</a>'s financial data — processing invoices, receipts, policy documents, and transaction records.</p></li><li><p>Optimize retrieval quality through embedding model selection, chunk strategy, metadata filtering, and re-ranking techniques.</p></li><h3>ML Model Serving &amp; Operations</h3><li><p>Collaborate with data scientists to take trained ML models from experimental notebooks to production serving infrastructure.</p></li><li><p>Build and maintain model serving endpoints with appropriate latency SLOs, input validation, and output monitoring.</p></li><li><p>Implement model performance monitoring and data drift detection to ensure production models remain accurate over time.</p></li><li><p>Support model retraining workflows by designing clean data pipelines and feature engineering that can be continuously updated.</p></li><h3>Backend Integration &amp; Reliability</h3><li><p>Integrate AI services cleanly with <a href="https://himalayas.app/companies/jeeves">Jeeves</a>'s backend microservices — designing clear API contracts, circuit breakers, and graceful degradation patterns.</p></li><li><p>Write high-quality, testable backend code in Python or Go/Node.js to power AI-integrated features.</p></li><li><p>Instrument AI components with structured logging, distributed tracing, latency dashboards, and alerting to ensure operational visibility.</p></li><li><p>Build human-in-the-loop review workflows for AI decisions that require oversight — particularly for high-value financial actions.</p></li><h3>Collaboration &amp; Growth</h3><li><p>Partner with Product, Backend Engineering, and Data Science to define the AI roadmap and translate requirements into reliable systems.</p></li><li><p>Contribute to a culture of quality by writing design docs, reviewing peers' AI system designs, and sharing learnings openly.</p></li><li><p>Help grow the AI engineering practice at <a href="https://himalayas.app/companies/jeeves">Jeeves</a> by establishing patterns, tooling, and best practices that the broader team can build on.</p></li></div></ul><h3>Requirements:</h3><ul><div><h3>Minimum Requirements</h3><li><p>Bachelor's degree in Computer Science, Engineering, or a related field — or equivalent practical experience.</p></li><li><p>5+ years of professional software engineering experience, with at least 3 years focused on AI/ML systems in production.</p></li><li><p>Hands-on experience building and deploying LLM-powered applications using APIs such as OpenAI, Anthropic, or Cohere in a production environment.</p></li><li><p>Experience designing and operating RAG pipelines, including chunking strategies, embedding models, and vector database integration (Pinecone, Weaviate, pgvector, or similar).</p></li><li><p>Strong proficiency in Python for AI/ML workloads; familiarity with at least one AI orchestration framework (LangChain, LlamaIndex, or equivalent).</p></li><li><p>Experience with ML model serving infrastructure: REST or gRPC inference endpoints, input/output validation, latency budgeting, and monitoring.</p></li><li><p>Solid backend engineering fundamentals: REST APIs, relational databases (PostgreSQL preferred), async patterns, and cloud infrastructure (AWS, GCP, or Azure).</p></li><li><p>Experience with observability tooling: structured logging, distributed tracing, and building dashboards for AI system health.</p></li><h3>Preferred Qualifications</h3><li><p>Experience in fintech, financial services, or any regulated industry where AI reliability and auditability are critical.</p></li><li><p>Familiarity with prompt evaluation frameworks, A/B testing AI outputs, and tracking model performance degradation in production.</p></li><li><p>Experience with ML lifecycle management tools: MLflow, Weights &amp; Biases, Vertex AI, or SageMaker.</p></li><li><p>Knowledge of real-time data streaming (Kafka, Kinesis) for event-driven AI pipelines.</p></li><li><p>Contributions to open-source AI tooling, published technical writing, or talks at AI/ML conferences.</p></li><li><p>Prior startup or scale-up experience — comfortable with ambiguity and building foundational systems from scratch.</p></li></div></ul></div><p>Originally posted on <a href="https://himalayas.app">Himalayas</a></p>