Senior AI Engineer

💻 Remote | LatAm - WE ARE EXCLUSIVELY CONSIDERING APPLICATIONS FROM INDIVIDUALS CURRENTLY RESIDING IN LATAM. ❗️ONLY ENGLISH RESUMES WILL BE CONSIDERED 🗣️ PLEASE NOTE THAT THIS ROLE REQUIRES ENGLISH PROFICIENCY (C1-C2 LEVEL) About Motum Motum connects experienced developers, engineers, and technical professionals with US companies building committed, long-term tech teams. Our roles are fully remote and full-time, designed for people who want real ownership, meaningful work, and the opportunity to grow inside US-based dynamic teams. When you join Motum , you work full-time with one company, integrate directly into their team, and build a career with long-term impact. Ready to join us? About the Client Our client is a fast-growing US fintech AI company building intelligent software for modern financial teams. Its platform brings together financial, operational, and customer data to help companies automate complex workflows, identify risk, and make faster decisions. The team is now expanding its AI capabilities across document intelligence, financial research, data retrieval, and workflow automation. You will join a small product-focused engineering team where AI is a core part of the product rather than an experimental feature. Your work will move directly into production and be used in high-trust financial workflows where accuracy, security, and reliability matter. About the Role We are looking for a Senior AI Engineer to design, build, and operate production-grade LLM applications and AI agents. You will develop retrieval and knowledge systems, connect language models to financial data and external tools, and create agent workflows that can complete complex tasks reliably. You will also establish the evaluation, observability, and security practices needed to run these systems in a fintech environment. This role is best suited to an engineer who has already shipped generative AI features into production and understands the difference between a successful prototype and a dependable product. Responsibilities Build production LLM applications for financial research, document processing, decision support, and workflow automation Design RAG pipelines using document ingestion, chunking, metadata filtering, embeddings, reranking, and hybrid search Develop AI agents that use APIs, databases, internal services, and external tools to complete multistep tasks Implement structured outputs, tool calling, memory, state management, retries, and human approval flows Build evaluation suites for retrieval quality, factual accuracy, task completion, latency, and cost Create safeguards for hallucinations, prompt injection, sensitive financial information, and unauthorized tool access Design and maintain Python services using FastAPI and PostgreSQL Deploy, monitor, and improve AI workloads in a cloud environment Collaborate directly with product managers, engineers, and company leadership Review architecture decisions and help establish engineering standards for the company's AI platform Qualifications 5+ years of professional software engineering, machine learning engineering, or applied AI experience 2+ years building applications with large language models Experience shipping at least one LLM-powered product or major feature to production Advanced Python skills and experience designing maintainable backend services Strong knowledge of RAG architecture, embeddings, vector search, reranking, and document processing Production experience with OpenAI, Anthropic, or comparable model APIs Experience building agent workflows with LangGraph, LangChain, LlamaIndex, or similar frameworks Experience designing and consuming REST APIs with FastAPI Strong working knowledge of PostgreSQL and data modeling Experience with at least one vector search technology, such as pgvector, Pinecone, Weaviate, or OpenSearch Experience deploying and monitoring applications on AWS, GCP, or Azure Understanding of testing, observability, security, and cost management for production AI systems Ability to explain technical tradeoffs clearly in English and collaborate with a distributed US team Nice To Have Experience building AI products for fintech, banking, payments, lending, risk, fraud, accounting, or financial operations Experience working with financial documents, transaction data, or other sensitive information Experience with LangGraph, MCP, and agent orchestration Experience with hybrid search, knowledge graphs, or advanced retrieval techniques Experience building automated LLM evaluation and regression-testing systems Experience with multimodal models and document intelligence Familiarity with SOC 2, data privacy, audit logging, or regulated software environments Experience optimizing inference latency and model usage costs Familiarity with Docker, Kubernetes, Terraform, and CI/CD pipelines We Offer 🏡 WFH 🏝️ 80 hours PTO + vacation days 🚀 Grow along a top US company and shape its future 📈 Career Advancement Opportunities The chance to help shape an AI-first fintech product during an important stage of growth Meaningful ownership over production AI systems Direct collaboration with the client's product and engineering teams Originally posted on Himalayas