Senior AI Engineer
Remote • São Paulo • Full-time
Posted 7d ago
Job Location
São Paulo
Tech Stack
Remote Work Policy
Fully remote
Employment Type
Full-time
Categories
AI Engineer
About the job
Jeeves is seeking a Senior AI Engineer to own AI workflows end-to-end, from design and implementation to measurement and continuous improvement. This hands-on role requires an AI-native approach, utilizing coding agents and AI tools daily to drive efficiency. You will collaborate closely with Product and Backend Engineering teams, taking initiative to define and build solutions rather than waiting for detailed specifications. The position is ideal for individuals who thrive on solving complex problems and are looking for a steep learning curve in a fast-growing fintech company.
Responsibilities
- Design agentic and LLM-based systems for multi-step work with human-in-the-loop components.
- Write design documents, make build-vs-buy decisions, and define success metrics for AI workflows.
- Build production-grade LLM pipelines, including prompt and context design, structured outputs, validation, and fallbacks.
- Integrate AI services with the company's backend, ensuring clear API contracts, retries, and data isolation.
- Manage AI model costs and latency, selecting appropriate models for different tasks.
- Develop evaluation sets and automated tests to monitor and prevent regressions in AI workflows.
- Instrument AI components with logging, tracing, dashboards, and alerts for quality monitoring.
- Maintain an audit trail of AI decisions to meet regulatory standards for financial products.
- Establish patterns, shared tooling, and best practices for AI engineering within the team.
- Guide the team on effective use of coding agents and AI tools in daily engineering tasks.
- Review AI system designs from peers and share learnings openly.
Requirements
- 7+ years of professional software engineering experience.
- At least 2 years of experience building and operating LLM or AI-powered systems in production.
- Proven track record of owning large systems or workflows end-to-end with limited direction.
- Hands-on experience shipping LLM-powered applications using APIs like Anthropic or OpenAI.
- Experience with structured outputs, error handling, and evaluation for LLM applications.
- Experience designing agentic or multi-step AI workflows, including tool use and orchestration.
- Strong proficiency in Python.
- Solid backend fundamentals, including REST APIs, relational databases (e.g., PostgreSQL), async patterns, and major cloud providers (AWS, GCP, Azure).
- Experience with observability for AI systems (logging, tracing, dashboards, quality monitoring).
- Professional fluency in English, both written and spoken.