:

Role Profile

We are seeking an experienced Snowflake Data Engineer to support delivery of a Regulatory Document Intelligence Proof of Concept (PoC). The role will design and build secure, scalable capabilities for document ingestion, processing, metadata enrichment, semantic search, and AI- enabled services within Snowflake.

Working across Snowflake, Cortex, AWS, Python, and relevant technologies, the role will establish and demonstrate a viable technical foundation for regulatory document intelligence.

Typical Accountabilities and Specific Responsibilities

- Implement Snowflake Cortex capabilities for document intelligence, content extraction, chunking, embeddings, semantic search, and vector search
- Design, develop, and optimise Snowflake-based data pipelines and ELT processes for structured and unstructured regulatory content.
- Build secure integrations with AWS services and enterprise document repositories, including event-driven ingestion patterns.
- Develop Python-based data engineering, processing, testing, and automation components.
- Support metadata extraction and enrichment, document classification, and preparation of AI-ready datasets.
- Enable AI/ML and retrieval-augmented generation (RAG) use cases using governed regulatory data and document content.
- Contribute to solution design, technical documentation, testing, CI/CD, security controls, monitoring, and operationalisation.




- Work with architects, data engineers, AI specialists, and business stakeholders to validate requirements and demonstrate PoC outcomes.

Essential

Strong hands-on experience with Snowflake, Snowpark, and Snowflake Cortex.

- Practical experience with semantic search, vector search, embeddings, and unstructured document processing.
- Advanced proficiency in Python, SQL, and modern data engineering practices.
- Experience integrating AWS services, particularly Lambda, S3, and event-driven architectures.
- Experience with source control, automated testing, CI/CD, DevOps, monitoring, and production support.
- Understanding of cloud security, access controls, data protection, and secure handling of sensitive content.

Essential

Experience designing AI/ML or retrieval-augmented generation solutions.

- Knowledge of document parsing, OCR, content classification, metadata frameworks, and document life-cycle management.
- Experience working with regulated, sensitive, or highly governed data environments.
- Familiarity with data lineage, auditability, role-based access control, and enterprise data governance.
- Experience delivering rapid prototypes that can transition into scalable production solutions.
- Strong knowledge of ETL/ELT, data modelling, metadata management, API integration, and pipeline orchestration.

📌 Snowflake Engineer (Barcelona)
🏢 Virtusa Europe
📍 Barcelona