Senior Data Engineer (GenAI / LLM)

DCG is a company focused on aligning business needs with people's ambitions, helping candidates find suitable environments for growth and assisting companies in building effective teams through close collaboration and attentive listening.

• Hands-on experience building LLM-powered automation for engineering workflows (e.g., review gates, quality checks, assistant tooling for dev/test/docs)
• Experience with AI-assisted review/approval flows and integrating AI steps into CI/CD-style pipelines
• Experience with AI-assisted test generation and test automation concepts
• Strong engineering discipline around quality and safety for AI outputs (evaluation mindset, reproducibility, traceability)
• Strong experience in data engineering and distributed processing; practical delivery mindset
• Hands-on experience with Kafka and SQL-based transformations
• Experience with batch/stream processing frameworks (e.g., Flink or Spark)
• Familiarity with schema formats and lifecycle (e.g., JSON/Avro/XSD) and versioning/compatibility concepts
• Experience working with Git workflows and Kubernetes environments
• CI/CD and build pipeline experience (Bazel + Tekton)

Nice to have:

• Experience with Data Reference Architecture / data product model
• Knowledge of Airflow, Snowflake, Iceberg, or similar data platforms
• Exposure to data governance, metadata, and lineage concepts
• Experience in banking or other regulated environments

• Design and implement LLM- and agent-assisted workflows to improve developer productivity and reliability of data pipeline delivery
• Build and enhance AI-driven automation for engineering processes, including pull request automation, quality gates, and assistive development tooling
• Implement AI-supported schema review and governance gates within the canonical message lifecycle
• Drive AI-powered test automation, including automated E2E test generation and quality validation
• Develop and maintain data packaging pipelines transforming source data into canonical message formats aligned with Data Packaging Framework and Availability Layer patterns
• Build and manage SQL-based data transformations and configuration-driven pipelines
• Support the canonical message lifecycle, including schema validation, versioning, compatibility checks, and publishing workflows
• Contribute to framework releases, operational stability, and documentation
• Maintain and update Architecture Decision Records (ADRs)