Context Trainer

By clicking the “Apply” button, I understand that my employment application process with Takeda will commence and that the information I provide in my application will be processed in line with Takeda’s [Privacy Notice](https://jobs.takeda.com/privacynotice) and [Terms of Use](https://www.takeda.com/terms-and-conditions/).  I further attest that all information I submit in my employment application is true to the best of my knowledge. **Job 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).  * Implement curation workflows and retention policies.  **Retrieval Quality**  * Run A/B experiments across vector stores; monitor answer quality vs. cost/latency; recommend defaults.  * Analyze failure cases and propose data-driven improvements.  **Data Governance**  * Enforce data minimization, retention, and access controls; maintain lineage and approvals per RAI (Responsible AI).  * Document data sources and usage for audit readiness.  SKILLS & QUALIFICATIONS  **Required**  * 3+ years data/ML experience with embeddings/retrieval expertise; strong documentation and runbook skills.   * Experience with content transformation, metadata extraction, and labeling workflows.  * Familiarity with privacy and data governance principles.  * Hands-on experience with vector stores (OpenSearch/pgvector/Kendra/Chroma) and labeling tools.  * Experience with REST APIs and data extraction from enterprise systems.  * Python coding proficiency for data pipelines and automation.  **Preferred/Nice to have**  * Experience designing golden datasets and evaluation pipelines.  * AWS Bedrock Knowledge Bases experience.  * Familiarity with software development lifecycle and technical documentation patterns.  **Locations** ------------- IND - Bengaluru **Worker Type** --------------- Employee **Worker Sub-Type** ------------------- Regular **Time Type** ------------- Full time