Experience Level: 68 years
Primary Skill: PostgreSQL, AWS, Amazon Bedrock
Responsibilities
- Design, develop, and maintain data pipelines supporting GenAI applications and RAG workflows
- Integrate structured and unstructured data from multiple sources into PostgreSQL and cloud storage
- Prepare and optimize datasets for LLM training, inference, and analytics
- Implement ETL/ELT processes and data transformation workflows using AWS services (S3, Lambda, Glue, Step Functions)
- Ensure data quality, validation, and consistency across pipelines
- Support monitoring, logging, and troubleshooting of data workflows
- Collaborate with GenAI developers and architects to enable AI-driven solutions
Required Qualifications
- 5+ years of experience in data engineering or analytics
- Hands-on experience with PostgreSQL, including complex queries, indexing, and data modeling
- Strong experience with AWS data services (S3, Glue, Lambda, Redshift, Step Functions)
- Experience with data pipelines, ETL/ELT processes, and batch/streaming workflows
- Proficiency in Python, SQL, or similar languages
Preferred Qualifications
- Experience preparing datasets for GenAI or LLM applications
- Familiarity with vector databases or embeddings for RAG pipelines
- Knowledge of data governance, privacy, and security practices
- Experience with CI/CD for data pipelines and MLOps workflows
- AWS Certified Data Analytics or Solutions Architect certifications
