About the role
We are seeking an AI Data & Knowledge Engineer who can independently design and deliver scalable data pipelines and knowledge systems for enterprise AI use cases. This role combines core data engineering responsibilities such as building ETL/ELT pipelines, integrating large-scale datasets, and powering backend data platforms - with AI-specific capabilities like RAG, GraphRAG, and knowledge graph enablement. The ideal candidate can build reliable, governed, production-grade data foundations that support AI applications at scale.
Key Responsibilities:
- Design, build, and maintain scalable batch and streaming data pipelines to ingest, transform, and serve data for AI and analytics use cases.
- Own end-to-end ETL/ELT workflows for domain data, including ingestion from enterprise systems, cleansing, transformation, enrichment, and publishing.
- Build AI-ready datasets and retrieval pipelines that support RAG, GraphRAG, semantic search, and knowledge-driven applications.
- Develop and manage knowledge graphs, ontologies, metadata layers, and data contracts for assigned domains.
- Implement and support vector indexing, chunking, hybrid retrieval, and backend data preparation workflows for AI services.
- Own integration patterns between source systems, data platforms, and AI application layers, including MCP server integrations where relevant.
- Monitor pipeline health, data quality, latency, throughput, and reliability; troubleshoot production issues and optimize performance.
- Mentor junior engineers and contribute to best practices for data engineering, data governance, and AI data enablement.
Required Qualifications:
- Bachelor's or Master's degree in Computer Science, Data Engineering, Information Systems, or a related field.
- 5-10 years of experience in data engineering, platform engineering, or backend data systems.
- Strong hands-on experience with Python and SQL.
- Experience building production ETL/ELT pipelines and scalable data integration workflows.
- Experience with big data and distributed processing frameworks such as Spark, Databricks, Hadoop ecosystem components, or equivalent platforms.
- Familiarity with workflow orchestration tools such as Airflow or similar.
- Experience working with cloud data platforms, warehouses, or lakehouses such as Snowflake, Databricks, BigQuery, Redshift, or equivalent.
- Understanding of data contracts, metadata management, data lineage, and data governance practices.
- Hands-on exposure to RAG, GraphRAG, vector databases, or knowledge graphs in enterprise settings is preferred.
- Experience with streaming/event-driven patterns using Kafka, Kinesis, or similar tools is a plus.
- Cloud certifications in AWS and/or Azure are a plus.
Work Schedule:
On-premise