AI Engineer

• Own finance AI workflows end to end, from problem definition through production and ongoing improvement
• Design agentic and LLM-based systems combining extraction, retrieval, reasoning, and tool use
• Define human-in-the-loop points for high-value financial decisions
• Write design documents, make build-vs-buy and model choices, and set workflow success metrics
• Work directly with customers and internal finance users to identify workflow problems and define completion criteria
• Build production-grade LLM pipelines with prompt and context design, structured outputs, validation, fallbacks, and confidence scoring
• Design retrieval and RAG components including chunking, embeddings, vector search, and re-ranking
• Integrate AI services with backend systems using API contracts, retries, graceful degradation, and per-customer data isolation
• Manage model cost and latency
• Build evaluation sets and automated evaluations, and catch regressions
• Implement logging, tracing, dashboards, alerts, and AI quality monitoring
• Maintain an audit trail of AI decisions for a regulated financial product
• Establish shared AI engineering patterns, tooling, and practices
• Train the wider team on effective use of coding agents and AI tools
• Review AI system designs and share learnings

• 7+ years of professional software engineering experience, including at least 2 years building and operating LLM or AI-powered systems in production
• Track record of owning a large system or workflow end to end, from scoping and design through launch and iteration, with limited direction
• Hands-on experience shipping LLM-powered applications with APIs such as Anthropic, OpenAI, or similar, including structured outputs, error handling, and evaluation
• Experience designing agentic or multi-step AI workflows, or RAG systems with vector databases such as pgvector, Pinecone, or Weaviate
• Strong proficiency in Python
• Solid backend fundamentals: REST APIs, PostgreSQL or similar relational databases, async patterns, and a major cloud provider such as AWS, GCP, or Azure
• Regular use of AI coding agents and tools such as Claude Code, Cursor, or Codex
• Experience with observability for AI systems: logging, tracing, dashboards, and quality monitoring
• Professional fluency in English, written and spoken

• Remote work or hybrid work based out of São Paulo
• Flexible schedule for coming into the office at complexo JK Iguatemi
• Opportunity to work at a stablecoin-native banking platform serving global enterprises
• Steep learning curve and hands-on experience with production AI systems