• Drive the technical vision and architecture for the Admin Copilot Conversational backend • Own end-to-end delivery of complex, cross-cutting features • Be a hands-on technical leader: set engineering standards • Collaborate closely with ML Scientists, Product Management, and Design • Influence technical direction beyond your team • Design and improve evaluation frameworks, guardrails, and safety mechanisms • Mentor and grow engineers on the team

• Projetar, implementar e manter infraestrutura escalável e confiável utilizando arquitetura Serverless na AWS • Desenvolver arquiteturas orientadas a eventos (EDA), criando sistemas que respondem a gatilhos em serviços distribuídos e sistemas externos • Colaborar com equipes multifuncionais para garantir a entrega eficiente e contínua de projetos de software • Otimizar funções Lambda para garantir alto desempenho, tempos mínimos de cold start e utilização eficiente de recursos • Gerenciar API Gateways, implementando autenticação, rate limiting, cache e transformações de requisição/resposta • Orquestrar múltiplos serviços gerenciados em nuvem para criar ecossistemas de aplicações abrangentes • Focar na otimização de custos através do design de arquiteturas eficientes e alocação inteligente de recursos • Garantir a segurança das aplicações via políticas de IAM, criptografia e controles de rede • Participar ativamente de revisões de código, testes e depuração para assegurar a alta qualidade do software • Mentorar e fornecer suporte técnico aos membros menos experientes da equipe.

• Participate in technical discussions with the team. • Assist in the analysis and resolution of issues. • Ensure product quality, scalability, and adherence to best practices. • Provide visibility into your work. • Seek to understand and monitor application/product health metrics. • Participate in pairing, code reviews, and refinement sessions to discuss technical solutions, ensure quality, and share knowledge. • Continuously look for opportunities to improve our applications, processes, and customer experience.

• Design, build, and operate high-performance, low-latency services across the App Foundations portfolio — Python/Django, Go, MySQL/PostgreSQL, Kafka, Redis, and ElasticSearch — in close partnership with engineers, designers, PMs, and EMs across R&D. • Lead end-to-end delivery of platform features and stability workstreams — from tech design and PRR through launch, post-launch ops, and long-term ownership. • Raise the operational bar: drive SLO-backed reliability work on Tier-0 systems like Notifications and LMS, improve our observability and on-call posture, and reduce unplanned work on the systems you own. • Contribute to our LLM inference platform (LMS) — model routing and fallback, provider integrations (Azure OpenAI, Bedrock), batch/async inference, cost attribution, and the safety rails that let product teams ship AI features without reinventing the stack. • Build AI-native internal tools that change how the team operates: automated ticket triage, on-call copilots, post-mortem drafting, customer-request classifiers — following the precedent of our Nora workflow and existing Claude skills. • Mentor other engineers, drive tech design and PR reviews, and be a credible SME for the systems you own. • Partner with product managers, TPMs, and peer platform teams (Portal, Customer Journey, Data Security, FedRAMP) to land complex cross-team initiatives cleanly. • Participate in hiring: write questions, run loops, and help bring the next wave of AF engineers on board.