Job Title : Sr. Data & Knowledge Engineer Location: Oaks, PA
Duration : 6 Months
Salary Range: $50.00 - $52.00/Hour on W2 (Without Benefits). Applicants must be willing to work on W2
Experience Required: 10+ Years Skills: AI Agents, AI & GenAI Products and Tools Role Overview
The Senior Data & Knowledge Engineer will build the data and knowledge foundation required for reliable enterprise AI solutions, with particular emphasis on Retrieval-Augmented Generation (RAG), enterprise knowledge integration, content ingestion, embeddings, and AI-ready data pipelines. Key Responsibilities
Design data and knowledge architectures for AI and GenAI applications.
Build ingestion and transformation pipelines for structured and unstructured enterprise information.
Design RAG pipelines and enterprise knowledge-retrieval solutions.
Implement chunking, metadata, embeddings, indexing, retrieval, and reranking strategies.
Build and optimize vector-search capabilities.
Integrate databases, documents, APIs, knowledge repositories, and other enterprise sources.
Develop processes for improving knowledge quality, freshness, lineage, and traceability.
Support structured data integration for AI agents and applications.
Work with AI engineers to improve grounding and retrieval quality.
Implement appropriate access controls for enterprise knowledge.
Develop reusable data and knowledge components that can support multiple AI use cases.
Required Skills
Strong data engineering background.
Advanced Python and SQL.
Experience with modern data platforms and cloud-native data services.
Hands-on knowledge of RAG, embeddings, vector databases, semantic search, and information retrieval.
Experience processing structured and unstructured data.
Understanding of data quality, metadata, lineage, security, and governance.
Knowledge of AI agents and AI/GenAI products and tools.
Preferred Experience
8+ years in data engineering, information management, or knowledge engineering.
Experience developing production RAG solutions.
Familiarity with knowledge graphs and semantic technologies is desirable.