Job Description
Description
THE OPPORTUNITY
Curate and govern the context layer (RAG/KBs, embeddings, metadata, labeling) to improve answer quality and minimize hallucinations, while protecting data/PII.
RESPONSIBILITIES
Curation & Labeling
Extract and curate content from enterprise sources (Confluence, Jira, SharePoint, ServiceNow,qTest) using APIs and automation.
Define chunking and metadata schemas; labeling guidelines; golden Q&A and evaluation sets.
Implement chunking strategies for diverse content types (code repositories, technical documentation, tickets, test cases).
Implementcurationworkflows and retention policies.
Retrieval Quality
Run A/B experiments across vector stores;monitoranswer quality vs. cost/latency; recommend defaults.
Analyze failure cases and propose data-driven improvements.
Data Governance ...
Ready to Apply?
Take the next step in your AI career. Submit your application to Takeda today.
Submit Application