• Design, build, and operate production-grade AI/ML systems that power Asteri’s orchestration platform • Collaborate closely with backend, platform, and frontend engineers to integrate AI capabilities into scalable, reliable product workflows • Deploy and iterate on LLM-based applications in production, continuously evaluating quality, latency, and cost • Own retrieval and agentic systems (e.g., RAG pipelines, workflow agents, policy-driven logic) end-to-end • Define and run rigorous evaluation and testing for AI systems, including offline experiments and production monitoring • Improve model performance and system behavior over time through experimentation, tuning, and system-level optimizations • Implement strong engineering practices for AI development, including testing, CI/CD, versioning, and rollback strategies • Stay current with advances in applied AI and generative models and translate relevant techniques into practical product improvements • Partner with cross-functional teams to understand product requirements and translate them into robust AI solutions

• Own end-to-end delivery of ML-based safety features, from technical design through production rollout and iteration • Build and maintain ML models that safeguard AI-generated content across multiple modalities (images, video, audio, text), detecting harmful content, IP violations, bias, and other safety concerns • Design and implement RAG (Retrieval-Augmented Generation) architectures and other advanced ML systems to enhance detection capabilities • Fine-tune and evaluate LLM-based models for content moderation and prompt filtering, making data-driven decisions about model selection and optimization • Collaborate with Legal, Product Policy, and AI product teams to define requirements, balance safety with user experience, and deliver compliant solutions • Create evaluation frameworks to measure model quality, safety coverage, false positive/negative rates, and policy alignment • Monitor production systems, respond to incidents, and maintain operational excellence through documentation and runbooks

• Propose and prototype innovative solutions to solve real-world problems, leveraging the latest state-of-the-art techniques in the field • Develop and maintain core ML pipelines • Train and deploy deep learning models for real-time applications • Collaborate cross-functionally with camera, systems and labeling teams • Curate datasets for evaluating performance and comparing performance trends over time • Provide technical mentorship to other junior ML engineers

• Atuar com desenho e implementação de soluções GenAI/Agentic utilizando Google Cloud ADK (planejamento de agentes, tool use, orquestração); • Construir workflows de agentes para extrair metadados de fontes estruturadas e não estruturadas e gerar descritores compatíveis com ODPS (YAML/JSON); • Integrar entregáveis com Dataplex (registro em catálogo, empacotamento/exportação de metadados, versionamento quando aplicável); • Implementar gates de validação: validação de schema, verificação de campos obrigatórios e suporte a processos human-in-the-loop (Publish Gate); • Colaborar com times internos para garantir aderência aos padrões de dados, qualidade e governança; • Desenvolver mecanismos de avaliação e mensuração de outputs de IA (métricas de qualidade, test sets, ciclos de iteração).