Data Engineer I (R-19886)

Identify prospective sources that can feed AI solutions and Research and Managed Services workflows

Define and apply source-evaluation criteria covering relevance, authority, freshness, completeness, coverage, consistency, accessibility, legal or licensing constraints, privacy, security, and technical compatibility

Perform source profiling, sample validation, proof-of-concept testing, and comparative assessments before recommending onboarding

Document source decisions, metadata, lineage, ownership, limitations, refresh expectations, and approved use cases

Implement and support AI-enabled workflows using LangChain or equivalent orchestration frameworks, large language models, embeddings, retrieval-augmented generation, vector databases, and prompt-engineering approaches where applicable

Monitor source and AI-workflow performance and recommend remediation, replacement, or additional sources when quality or coverage falls below requirements

Perform day-to-day operational activities supporting Research and Managed Services, including monitoring, exception handling, data maintenance, and issue resolution

Perform database administration activities, including performance tuning and implementation of best practices

Implement new data-maintenance processes and provide end-to-end process ownership

Ensure data integrity by validating, reconciling, and regularly cleaning data

Investigate and resolve production incidents, pipeline failures, data-quality issues, and operational exceptions

Follow applicable data governance, security, and operational standards

Evaluate and implement new technology solutions, and proactively learn and adopt new tools, platforms, and methodologies introduced by the organization

Communicate with stakeholders and conduct knowledge-exchange sessions for technical and non-technical audiences

Develop and maintain data documentation, including data dictionaries, source assessments, data-flow diagrams, data mappings, runbooks, and data lineage

Collaborate with cross-functional teams across Data & Analytics, Technology, Research Services, Managed Services, Product, and Data Governance

Additional duties as assigned.

Strong SQL and Python skills, with demonstrated ability to write and maintain code as a core part of daily work

Experience with Playwright, Selenium, and other web-data collection techniques

Experience developing and supporting data-ingestion, transformation, and ETL/ELT workflows

Ability to collect and interpret data from multiple sources, including web scraping and GCS/S3, and formats including delimited files, XML, JSON, and PDF

Working knowledge of data systems and databases used to maintain data pipelines

Experience with Power BI, Tableau, or other dashboard tools

Experience managing stakeholders and project plans

Proficiency in Microsoft Office Suite

Willingness and demonstrated ability to learn new technologies as they are introduced

BigQuery experience and knowledge of AWS and/or GCP

Hands-on experience implementing AI solutions using LangChain or an equivalent orchestration framework

Exposure large language models, prompt engineering, retrieval-augmented generation, embeddings, vector databases, AI agents, or graph databases

Knowledge of Data Operations methodologies, data management approaches, ServiceNow, and/or Jira

Experience with NoSQL technologies, SQL Server administration, R programming, web technologies, and data mapping from multiple sources.