- Serve as a resource for creating AI agents and RAG databases to solve problems. Develop AI Agent tools to automate the retrieval, wrangling, and analysis of data. - Utilize combined knowledge of data structures, analytics, algorithms/models, and strong computer science fundamentals to prepare datasets, conduct analytics, and develop deployable solutions with guidance from more senior resources. - Able to analyze and prepare complex and new data sources and incorporate them into analytical solutions. - Collaborate with customers and key stakeholders on initiating ideas, performing design, analysis, and process improvement. - Develop and deploy AI and ML solutions on Google Cloud Platform. - Utilize massive data sources to craft business insights and features for innovative solutions. - Understand diverse data sources, both structured and unstructured.

• Own end-to-end data science initiatives • Build, operationalize, and improve machine learning models • Evaluate and interpret the performance of ML models • Conduct deep-dive analyses using advanced statistical methods • Apply statistical modeling and AI-assisted analytics • Communicate findings clearly to executives and stakeholders • Contribute to technical best practices and team standards • Partner with Data Engineering, Analytics, and Governance

• Ensure the integrity, accuracy and compliance of clinical trial data • Assist during a study database in RAVE to include but not limited to: • Review protocols for appropriate data capture including electronic Case Report Form (eCRF) design • Assist with the development of data edit check specifications and data listings • Perform User Acceptance Testing (UATs) of Electronic Data Capture (EDC) systems according to company processes • Assist with the review of migration reports to ensure database build accuracy • Perform reconciliation of data from external data sources against the clinical database • Perform Serious Adverse Event reconciliation activities according to SOPs and guidelines • Execute data cleaning and discrepancy management to ensure compliance with the protocol • Track and report study metrics to internal and external stakeholders • Create or update Data Management Plan (DMP), Data Review Plan (DRP), eCRF Completion Guidelines (eCCGs) and other Data Management required study documents • Perform database lock and freeze activities per company SOPs

• Projetar e implementar pipelines de validação de dados e avaliação de modelos em ambiente cloud (AWS). • Integrar dados e métricas de avaliação em um fluxo automatizado e auditável. • Modularizar o pipeline para facilitar reuso, testes e manutenção. • Trabalhar em colaboração com times de Data Science, Engenharia de Dados e Produto. • Garantir boas práticas de versionamento, logging, monitoramento e testes automatizados. • Propor melhorias contínuas na arquitetura de dados e nos processos de validação.