What are the responsibilities and job description for the AI Data Engineer position at Ranger Technical Resources?
AI Data Engineer #2646
Position Summary:
A growing SaaS organization in the legal and professional services industry is building its first centralized AI-ready data platform and is hiring a Senior AI Data Engineer to help architect and scale the foundation from the ground up. This role combines modern AWS data engineering with applied GenAI development. You’ll build scalable lakehouse infrastructure, develop dbt powered data models, create CDC and ingestion pipelines, and help design RAG based AI workflows that power intelligent product experiences. This is a highly hands on, greenfield engineering role ideal for someone who enjoys solving complex data problems, making architectural decisions, and building systems that directly enable AI capabilities across a multi-tenant SaaS environment.
Experience and Education:
- BS in Computer Science, Information Technology, Engineering or equivalent experience/field
- Hands on experience building AWS based data platforms in production environments
- Proven experience with dbt, SQL and Python in modern lakehouse or analytics ecosystems
- Experience designing scalable data ingestion and CDC pipelines
- Exposure to production GenAI or RAG implementations
- Background working within SaaS, legal tech, fintech, or regulated environments is highly preferred
Skills and Strengths:
- AWS
- dbt
- SQL
- Python
- Airflow
- MWAA
- Redshift
- Athena
- Glue
- S3
- CDC
- Iceberg
- RAG
- LangChain
- OpenSearch
- Embeddings
- Vector Databases
- Data Modeling
- Multi-tenant SaaS
- Lakehouse Architecture
Primary Job Responsibilities:
- Architect and expand a centralized AWS lakehouse platform
- Develop scalable Bronze, Silver, and Gold data models using dbt
- Build ingestion and CDC pipelines across SQL Server and SaaS platforms
- Design and maintain orchestration workflows using Airflow/MWAA
- Support Redshift, Athena, Glue, S3, and Iceberg-based analytics infrastructure
- Build embedding, retrieval, and vector search pipelines for structured and unstructured data
- Design RAG workflows that support AI-powered product experiences
- Implement governance, IAM, encryption, and tenant isolation best practices
- Improve observability, reliability, and scalability across data systems
- Partner with engineering and product leadership on AI platform strategy and architecture
- Help establish engineering standards and best practices within a growing AI ecosystem
- Contribute to future AI agent and MCP-style integrations