• Establish and maintain enterprise-level data management practices toward Level 4-5 CMMI target operating maturity. • Identify and document authoritative data sources across the OAA application and reporting portfolio. • Standardize data definitions and establish enterprise data standards and naming conventions. • Resolve duplicate and conflicting data elements across applications, databases, and reports. • Fill metadata gaps and maintain data dictionaries and report-to-data-source traceability. • Identify and remediate reporting inconsistencies across SSRS, Power BI, SharePoint, and custom applications. • Support Azure Data Engineering activities, including data pipeline and data warehouse design considerations. • Produce and maintain the Data Management Assessment and supporting data governance artifacts. • Advise developers and Government stakeholders on data quality, data lineage, and governance impacts of proposed changes. • Support ATO artifact maintenance as it relates to data handling, PII, and data classification. • Participate in recurring technical working sessions with OAA leadership and the DMC team.

• Realizar estudos e análises para identificar gaps, inconsistências e oportunidades de melhoria nos dados cadastrais. • Construir modelos estatísticos e preditivos para inferência, recomendação e enriquecimento de dados. • Desenvolver modelos de Golden Record, garantindo a melhor versão do cadastro do cliente. • Utilizar técnicas de grafos para identificar relações complexas e oportunidades no Cadastro, como detecção de vínculos, clusters e padrões de relacionamento entre entidades. • Trabalhar com grandes volumes de dados estruturados e não estruturados. • Aplicar técnicas de data profiling, imputação e enriquecimento de dados. • Colaborar com áreas de negócio e engenharia para melhoria contínua da qualidade dos dados. • Apoiar iniciativas de governança e projetos de MDM (Master Data Management). • Documentar metodologias, processos e resultados de forma clara e acessível.

• The Data Scientist at Earnest LLC in Oakland, CA will guide product recommendations and model development, and communicate analyses and insights to the Data team and broader organization. • Develop and maintain predictive machine learning (ML) models to assess potential risks and opportunities across Earnest’s lending products, contributing to the enhancement of risk and marketing assessment procedures. • Participate in the end-to-end ML pipeline, spanning from data collection to model deployment. This includes collaborating with data and infrastructure engineers to automate training and monitoring using BI tools and writing ETL pipelines to source data for model training from various sources such as Earnest or Navient data warehouses, production databases, third-party providers, and publicly available datasets. • Conduct experimentation and execute causal inference analyses on pricing, marketing, and product models to optimize product conversion rates. • Write code for inferential models that guide product and underwriting decisions, and document modeling decisions through Confluence or GitHub Readme files. • Collaborate closely with cross-functional teams and stakeholders to accelerate solution iteration and achieve measurable outcomes. • Articulate model impacts and analytical insights through presentations and reports, draft recommendations to optimize product and underwriting policies, and provide guidance and mentorship on modeling best practices to peers on the team.

• Own the Permissions & Privacy Framework – Serve as the single business owner of client data permissions and governance, defining role-based access principles and clear decision rights. Evolve the framework as appropriate • Operationalize Access & Policy Management – influence the design and manage workflows for access provisioning, deprovisioning, temporary access, advisor transitions, and confidential client handling • Govern Ongoing Permission Decisions – Act as the central project manager for complex access requests. Maintain clear policy guidance for recurring scenarios. • Build Audit, Monitoring & Risk Controls – Establish audit processes, reporting, and monitoring to ensure consistency and detect inappropriate access • Drive Cross-System Alignment – Partner with Product and Technology teams to standardize permissions across all platforms and products • Enable the Organization – Partner to create training, guidance, and FAQs to ensure employees understand access policies and processes.