Data / Integration Engineer

Job Description Essential Job Functions: - Design, develop, and maintain scalable document ingestion and processing pipelines to support enterprise knowledge management and AI-powered applications. - Build and optimize multi-stage data workflows for extracting, transforming, enriching, and indexing content from diverse document formats including PDF, PPTX, DOCX, CSV, and image-based sources. - Implement advanced document processing capabilities, including metadata extraction, content chunking, classification, summarization, and information retrieval workflows. - Manage vector database indexing strategies and search optimization to ensure high-quality retrieval performance and relevance. - Develop and maintain MCP-compatible tool servers that securely expose enterprise databases, APIs, cloud platforms, and external services to AI agents. - Design and implement event-driven architectures leveraging messaging and integration services to enable scalable and responsive data processing solutions. - Create and deploy data analysis, document intelligence, and knowledge retrieval agents using reusable development templates and platform tooling. - Collaborate with cross-functional teams to deliver reliable, scalable, and innovative data engineering and AI-driven solutions. Basic Qualifications - Bachelor's degree in Computer Science, Data Engineering, Information Technology, Artificial Intelligence, or equivalent combination of education and experience. - Typically, 3+ years of professional experience in Python development and data pipeline engineering. - Hands-on experience designing and maintaining ETL/ELT workflows using orchestration platforms such as Dagster, Airflow, or equivalent technologies. - Strong proficiency with document processing frameworks and libraries for extracting and transforming content from structured and unstructured data sources. - Experience working with vector databases, embedding models, semantic search technologies, and retri