Senior Data Engineer (GenAI / AWS)

TheStaffed • Los Angeles, CA

2d

About The Position

Our client is seeking a Senior Data Engineer with 6–10 years of experience to design and build advanced data pipelines and AI-powered document-processing solutions on AWS. The role focuses on end-to-end workflows that integrate generative AI, vector databases, and RAG architectures to support intelligent agent systems.

The engineer will build scalable data pipelines and automated document-processing workflows, develop vector databases and knowledge bases for contextual retrieval, and build and deploy AI agents. The role also involves maintaining CI/CD pipelines and implementing infrastructure as code, while optimizing production pipelines for scalability, reliability, security, and performance.

Requirements

• 6–10 years of professional experience as a Data Engineer or in a similar role.
• Strong proficiency in Python, SQL, and TypeScript.
• Hands-on experience with AWS Lambda, S3, Step Functions, Glue, IAM, and Bedrock.
• Demonstrated expertise with vector databases such as Pinecone, pgvector, and OpenSearch, and with embedding technologies.
• Experience building RAG systems, knowledge bases, and semantic search solutions.
• Proficiency with LangChain, LlamaIndex, and Claude Agent SDK.
• Experience with Document AI, OCR technologies such as Textract, and NLP services such as Comprehend.
• Familiarity with infrastructure-as-code tools such as Terraform and AWS CDK, and CI/CD automation with GitHub Actions.

Responsibilities

• Design and develop scalable data pipelines using AWS Step Functions, Lambda, S3, Textract, and Comprehend to extract and process structured and unstructured data.
• Build automated document-processing workflows with document chunking, embeddings, vector indexing, and semantic search capabilities.
• Develop and maintain vector databases and knowledge bases to support RAG systems, and integrate them with AI agents for contextual information retrieval.
• Build and deploy AI agents using Claude Agent SDK and Amazon Bedrock AgentCore Runtime.
• Create and maintain CI/CD pipelines using GitHub Actions to automate builds, testing, and deployments.
• Optimize data pipelines for scalability, reliability, security, and performance across production environments.
• Implement infrastructure-as-code solutions using Terraform and AWS CDK for repeatable, maintainable deployments.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed