• Lead a team of 6 ML engineers to bring state of the art AI to Clio's clients, spanning traditional ML models, GenAI, and agentic AI. • Guide the team in designing and shipping agentic systems, including retrieval, tool use, orchestration, and the evaluation frameworks that keep them reliable and safe in production. • Collaborate cross-functionally with MLOps engineering, product management, operations, and data science to identify new tooling for ML and LLM-driven features for Clio customers. • Work in an agile environment with our team of ML engineers, ML ops, and full stack developers across a variety of projects. • Learn new things, challenge yourself, and hone your craft as an ML and infrastructure expert in a space that is moving fast. • Participate in diverse projects and collaborate with multiple engineering teams across three countries. • Review and provide feedback on code, both from within your own team or across all of Clio. • Collaborate with teams across Clio to diagnose, understand, and solve problems, and to build solutions that may span many areas. • Teach and learn from those around you, providing constructive feedback and taking on feedback to help grow.

• Atuar como referência técnica na arquitetura de dados e inteligência artificial da UniScale. • Projetar, desenvolver e evoluir a infraestrutura que sustenta as soluções baseadas em dados e IA. • Estruturar pipelines de dados, desenvolver modelos proprietários de Machine Learning. • Implementar práticas de MLOps, garantir a governança e a qualidade dos dados. • Disponibilizar serviços escaláveis que suportem produtos inteligentes. • Atuar como mentor técnico da equipe. • Promover a evolução das práticas de engenharia, inovação e desenvolvimento orientado por Inteligência Artificial.

• Build LLM applications. • Develop dialogue-based systems and semantic search and integrate them into the domain-specific applications of the industry solution. • Set up and maintain RAG systems, including knowledge-base management: indexing, updates, and clean source-separated storage of structured and unstructured content. • Operation and monitoring. • MLOps in production: observability, structured logging, and error analysis. • Ensure systems run reliably, not just that they worked once. • Deploy agents to production, from development and integration through to stable delivery. • Improve systems based on monitoring data, testing, and user feedback. • Identify new AI use cases, prototype them, and build data pipelines from preprocessing and model development to production.

• Architect, build, and deploy intelligent features to our VIP platform. • Collaborate with scientists to assess, fine-tune, and deploy LLMs on domain specific data. • Build and maintain Retrieval-Augmented-Generation (RAG) systems and Reinforcement Learning frameworks. • Integrate features into our platform with product and software engineers. • Establish prompt engineering and data management best practices. • Monitor and evaluate data and models across the model lifecycle. • Stay updated on advancements in NLP, LLMs, and agentic AI research.