Overview
Senior Data Engineer responsible for designing and building enterprise knowledge and context capabilities to enable reliable, scalable, governed AI solutions.
What you'll do
- Design and build foundational knowledge services for AI applications and agents to discover, retrieve, understand, and use enterprise information.
- Develop capabilities covering structured data, documents, terminology, reference data, metadata, semantic models, business rules, and domain-specific knowledge.
- Collaborate across data engineering, knowledge management, metadata, search, AI, and platform engineering teams to deliver reusable knowledge services.
- Translate business and scientific stakeholders’ domain knowledge into scalable data and AI capabilities.
- Implement technical depth and architectural thinking to support enterprise AI and data capabilities.
What you'll need
- Experience with Databricks, Apache Spark, Delta Lake, Unity Catalog, or comparable modern data platforms.
- Experience with cloud platforms such as AWS, including storage, compute, security, networking, and managed AI services.
- Experience processing unstructured content such as PDFs, Microsoft Word, presentations, web content, or scientific/technical documents.
- Understanding of search and information-retrieval concepts including indexing, relevance, filtering, ranking, and hybrid search.
- Experience with vector databases, embedding models, retrieval-augmented generation, semantic search, or large language model applications.
- Familiarity with metadata-management or data-governance platforms such as Collibra or equivalent tools.
- Experience implementing authorization, auditability, provenance, and governance for enterprise AI solutions.
Details
- Shifts enterprise knowledge and context capabilities for governed AI solutions.
- Location: Hyderabad, India.
Read the full description and apply on the company’s own careers page.
