Remote Role: Senior Data Engineer (GenAI / AWS) | Amazon Bedrock | Claude Agent SDK | Python | 12+ years of experience | Local to CA only

Responsibilities

Design and build scalable AWS data pipelines and automated document-processing workflows, including document chunking, embeddings, vector indexing, semantic search, and RAG solutions. Develop AI agents using the Claude Agent SDK on Amazon Bedrock AgentCore Runtime, integrate knowledge bases, and maintain CI/CD pipelines while optimizing for security, reliability, scalability, and performance.

Requirements

Requires 12 or more years of data engineering experience, strong Python and SQL skills, and expertise in AWS services, document AI, vector search, RAG, Amazon Bedrock, and the Claude Agent SDK. An AWS certification is required; experience with TypeScript, AWS Glue, OpenSearch, Pinecone, pgvector, LangChain, LlamaIndex, Terraform, or AWS CDK is beneficial.

Skills

• Python
• SQL
• AWS
• AWS Step Functions
• AWS Lambda
• Amazon S3
• Amazon Textract
• Amazon Comprehend
• Document AI
• Optical Character Recognition
• Vector Databases
• Embeddings
• Retrieval-Augmented Generation
• Amazon Bedrock
• Claude Agent SDK
• GitHub Actions

About this role

Job Description
Role: Senior Data Engineer (GenAI / AWS)
Duration: 3+ Months (Extension Possible)
Location: Los Angeles, CA (Remote/Hybrid) - Local to CA Only
Employment Type: C2C
Experience: 12+ Years
Note: AWS certification is required.
We are looking for a highly experienced Senior Data Engineer with strong expertise in AWS, Python, Generative AI, and Retrieval-Augmented Generation (RAG). The ideal candidate will design and build scalable AI-powered document processing solutions, vector search pipelines, and intelligent AI agents on AWS.
Key Responsibilities
Design and develop scalable data pipelines using AWS Step Functions, Lambda, S3, Textract, and Comprehend.
Build automated document-processing workflows for structured and unstructured data.
Implement document chunking, embeddings, vector indexing, semantic search, and RAG solutions.
Develop and maintain vector databases and knowledge bases.
Integrate knowledge bases with AI agents for contextual information retrieval.
Build and deploy AI agents using Claude Agent SDK on Amazon Bedrock AgentCore Runtime.
Develop and maintain CI/CD pipelines using GitHub Actions.
Optimize data pipelines for scalability, security, reliability, and performance.
Must-Have Skills
12+ years of Data Engineering experience.
Python, SQL
AWS Step Functions, Lambda, S3
Amazon Textract and Comprehend
Document AI / OCR
Vector databases and embeddings
Document chunking and indexing
Advanced retrieval and reranking
RAG and knowledge-base integration
Amazon Bedrock
Claude Agent SDK
AgentCore Runtime
GitHub Actions CI/CD
AWS IAM and API integrations
Good-to-Have Skills
TypeScript
AWS Glue
OpenSearch, Pinecone, pgvector
LangChain / LlamaIndex
Terraform / AWS CDK
Additional Information
All your information will be kept confidential according to EEO guidelines.

About TMS LLC

IT Services and IT Consulting · 51-200 employees · headquartered in Parsippany, New Jersey