AI Data Engineer

BayOne Solutions is seeking an AI Data Engineer to build and maintain data infrastructure supporting AI and machine learning initiatives. The role focuses on developing data pipelines for model training, retrieval-augmented generation, production ML systems, vector search, governance, and MLOps/LLMOps workflows.

Responsibilities:

• Design and build pipelines to ingest, clean, and transform structured and unstructured data (documents, PDFs, transcripts, logs) for AI/ML use cases
• Build and maintain vector embedding pipelines and support vector database integration
• Develop feature stores/pipelines for ML model training and inference
• Implement data pipelines supporting RAG architectures — chunking strategies, embedding refresh cycles, metadata tagging
• Partner with ML engineers/data scientists to understand data requirements for model training and evaluation
• Ensure data lineage, quality, and governance across pipelines feeding AI systems
• Optimize pipelines for cost and performance (e.g., Dynamic Tables, streaming ingestion)
• Support MLOps/LLMOps workflows — versioning datasets, tracking data used in model training for reproducibility and compliance
• Implement entitlement/access control logic so AI systems only access data they're authorized to use

Requirements:

• Strong SQL + one of Python/Scala for pipeline development
• Experience with a cloud data platform
• Experience with orchestration tools (Airflow, dbt)
• Understanding of embedding models, vector search, and RAG patterns
• Experience with unstructured data processing
• Familiarity with ML lifecycle concepts
• Experience with Snowflake Cortex, Cortex Search, or similar in-warehouse AI tooling
• Experience in a regulated industry (financial services) with data entitlement/compliance requirements
• Exposure to LLM application frameworks (LangChain, LlamaIndex)