Lead AI Engineer — Productivity Systems

Nubank; Campinas; Híbrido; BRL 300 000 - 540 000; Tempo integral

Vantagens oferecidas por esta oferta de emprego

Equity

Meal Card

Public Transportation

Medical Plan

Dental Plan

Work-from-home Allowance

Relocation Assistance

Resumo da oferta

Nubank is seeking an Applied AI Engineer to design and ship AI-powered agents and workflows that automate key internal processes. The role emphasizes production readiness, evaluation, and governance, with a focus on the AI layer rather than infrastructure.

You will work on prompts, context, and agent orchestration, integrating AI into business tools while maintaining strong software engineering practices and safety considerations.

Qualificações

• Shipped LLM systems in production and used by real users.
• Hands-on AI engineering: prompt/context engineering, tool calling, and agent frameworks.
• Experience measuring AI output quality: evals, test sets, feedback loops, failure mode awareness.
• Strong software engineering foundation: Python, TypeScript, or Clojure; solid API/integation skills.
• Ability to judge when to use LLM vs deterministic automation and product sense for AI solutions.

Responsabilidades

• Design, build, and ship LLM-powered agents and workflows that automate internal processes end-to-end.
• Work with frontier models and modern AI stack: tool calling, structured outputs, RAG, multi-agent orchestration.
• Define evaluation criteria and guardrails to ensure production-grade reliability.

Conhecimentos

Shipped LLM systems

Prompt & context engineering

API & integration skills

Python/TypeScript/Clojure

AI product sense

Ferramentas

n8n

Zapier

AWS

Descrição da oferta de emprego

About Nu

Nu is the leading digital bank in Latin America, serving 135 million customers across Brazil, Mexico, and Colombia. The company has been leading an industry transformation by leveraging data and proprietary technology to develop innovative products and services.

Nu is the leading digital bank in Latin America, serving 135 million customers across Brazil, Mexico, and Colombia. The company has been leading an industry transformation by leveraging data and proprietary technology to develop innovative products and services. Guided by its mission to fight complexity and empower people, Nu caters to customers’ complete financial journey, promoting financial access and advancement with responsible lending and transparency. The company is powered by an efficient and scalable business model that combines low cost to serve with growing returns. Nu’s impact has been recognized in multiple awards, including Time 100 Most Influential Companies, Fast Company’s Most Innovative Companies, and Forbes World’s Best Banks. Visit our Institutional Page

About The Role

We are looking for an engineer who has already built with AI in production. You have shipped LLM-powered systems (agents, copilots, RAG pipelines, or AI-driven automations), you know what breaks when they meet real users, and you know how to make them reliable enough for business-critical workflows.

Your day-to-day is applied AI engineering: designing agentic workflows, integrating LLMs into internal tools and business processes, building evaluation and guardrail layers, and turning manual, high-friction workflows into AI-assisted ones that thousands of Nubankers depend on.

This is not an infrastructure role. You will not spend your days on Terraform, IAM policies, or email deliverability. Cloud fluency helps, but the core of this job is the AI layer — prompts, context, agents, evaluations, integrations — and the product judgment to know where AI genuinely helps versus where deterministic automation is the right answer.

Key Responsibilities

Applied AI & Agentic Systems

• Design, build, and ship LLM-powered agents and workflows that automate complex internal processes end-to-end.
• Work hands-on with frontier models and the modern AI stack: tool/function calling, structured outputs, MCP, RAG, multi-agent orchestration.
• Own the full lifecycle of an AI system: from problem discovery and prototype to production hardening, monitoring, and iteration.

Evaluation & Reliability

• Build evaluation harnesses, guardrails, and quality feedback loops so AI systems can be trusted in production — not just demoed.
• Define what "good" looks like for non-deterministic systems and instrument it: evals, regression suites, human-in-the-loop review where it matters.

Intelligent Workflow Automation

• Use orchestration platforms (e.g., n8n) and custom integrations as delivery vehicles for AI-in-the-loop automation across business units.
• Integrate enterprise platforms (Slack, Google Workspace, Jira, internal APIs) into coherent, AI-assisted workflows.

AI Adoption & Governance

• Drive the technical strategy for AI adoption within engineering and business workflows.
• Develop governance frameworks that make AI coding assistants and agents safe, compliant, and effective — balancing developer freedom with security and operational risk.

Multiplier Work

• Create Golden Paths, reference implementations, and documentation that let other teams build AI workflows safely on their own.
• For Lead/IC6: act as the technical reference for applied AI in the domain, influence architecture beyond the immediate team, mentor senior engineers, and partner with ITSec and Privacy to align AI solutions with company policy.
• For Senior/IC5: execute complex AI projects with high autonomy, identify workflow bottlenecks worth automating, and mentor mid-level engineers.

What are we looking for?

Must Have — Demonstrated Applied AI Experience

• Shipped LLM systems in production: at least one real system with an LLM at its core — an agent, copilot, RAG application, or AI-driven automation — used by real users, not a proof of concept.
• Hands-on AI engineering: practical fluency with prompt and context engineering, tool/function calling, structured outputs, and agent frameworks or orchestration patterns.
• Evaluation mindset: experience measuring and improving AI output quality — evals, test sets, feedback loops — and an honest understanding of failure modes (hallucination, drift, prompt injection).
• Solid software engineering foundation: proficiency in Python, TypeScript, or Clojure; strong API and integration skills; the discipline to ship maintainable systems, not notebooks.
• AI product sense: the judgment to identify which problems deserve an LLM, which need deterministic automation, and which should not be automated at all.

Nice to Have

• Experience with workflow automation platforms (n8n, Zapier, or custom orchestration engines).
• Exposure to cloud services (AWS) and infrastructure-as-code.
• Familiarity with AI developer tooling (Claude Code, Cursor, Copilot) and AI governance practices.

Behavioral & Strategic Skills

• Builder bias: you prototype fast, validate with real users, and harden what works.
• Governance-aware: you understand that "efficiency" must be balanced with "security," and you can design AI systems that are safe by default without destroying velocity.
• Multiplier: you enjoy documenting your work, creating Golden Paths, and teaching others how to use what you build.
• Comfortable with ambiguity: AI capabilities shift monthly; you treat that as an opportunity to re-solve problems better, not as churn.

Our Benefits

• Chance of earning equity at Nubank
• Food/ Meal Card (Vale-Refeição and/or Vale Alimentação)
• Public Transportation Commuting Benefit (Vale-Transporte)
• NuCare – Psychological, Financial and Legal Assistance Program
• Life Insurance
• Medical Plan
• Dental Plan
• NuLanguage – Language Course Program
• Nucleo - Our learning platform of courses
• Extended Parental Leave
• Daycare Allowance
• Parental Consultancy
• Work-from-home Allowance
• Gym Partnerships
• 30 days of paid vacation
• Relocation Assistance Package, if applicable

Work Model for this Role

Our hybrid work model brings us to the office at least twice a week, on strategic days designed to maximize team connection and collaboration. For more details, visit https://building.nubank.com/nu-hybrid-work-model/

Our recruitment process may involve the use of artificial intelligence–enabled tools, such as automated interview transcription and analysis, to support the evaluation process. Artificial intelligence is not used to make final hiring decisions; all decisions are made by human reviewers.