• Ship production LLM agents with tool use: orchestration (state, pause/resume, journey/mode routing, failure handling) • MCP or gateway-style tool integration (schemas, auth, idempotency, audit) • Customized evals • Build alongside internal team

• Design, build, and deploy AI agent workflows that enable measurable efficiencies across business functions • Implement orchestration patterns including single-agent and multi-agent systems with appropriate state management • Integrate AI capabilities with existing tools and platforms via APIs, plugins, and function calling • Define and enforce guardrails for agent behavior, capabilities, and permissions in partnership with product and security • Build reusable automation patterns and templates that can be adopted across teams • Work alongside our data platform team to enable AI-driven analytics and reporting tools • Implement monitoring, observability, and feedback loops for deployed AI workflows • Ensure responsible AI practices, including fairness, transparency, and risk mitigation • Evaluate and recommend AI tooling, frameworks, and model providers based on business needs and cost • Stay current on industry trends, emerging AI capabilities, and best practices in automation engineering • Mentor engineers on integrating AI into their development workflows

• Desenvolver, validar e manter pipelines de MLOps, garantindo a automação de processos e integração com serviços da AWS. • Projetar e manter a arquitetura de sistemas, assegurando alinhamento com os objetivos dos projetos. • Garantir a sustentação e evolução da ferramenta de automação n8n. • Trabalhar em colaboração com cientistas de dados para operacionalizar modelos de machine learning. • Atuar na resolução de chamados relacionados ao time de MLOps. • Propor e desenvolver soluções técnicas (como aplicações web, APIs e agentes baseados em LLMs) para apoiar a área de Ciência de Dados.

**What You'll Do** - Define and drive the technical vision for ML solutions across products and platforms - Own the end-to-end software development lifecycle — from design and code reviews through to deployment and operations - Architect high-performance, scalable microservices, including synchronous and asynchronous web services - Build real-time inference pipelines for complex models using Triton, TensorRT, and mixed-precision computing - Mentor engineers, set technical direction, and foster a strong team culture - Champion engineering excellence, system resilience, and continuous operational improvement