Senior Data Engineer (GenAI / AWS)

ZealHire Inc.; Los Angeles (CA); Hybrid; USD 140,000 - 190,000; Part time

Job summary

ZealHire Inc. is seeking a Senior Cloud/Data Engineer to design and implement scalable data pipelines on AWS, leveraging Lambda, Step Functions, S3, Textract, and Comprehend. You will build document-processing workflows, embeddings, and vector indexing to enable advanced retrieval and AI agent interactions.

The role focuses on RAG-enabled knowledge bases, agent integration, and robust CI/CD with GitHub Actions, Terraform, and AWS CDK, in a hybrid environment for LA locals.

Qualifications

• Must have strong Python and SQL proficiency.
• Experience designing and building data pipelines on AWS.
• Familiarity with AI/ML document processing and retrieval systems.
• Knowledge of vector databases, embeddings and RAG concepts.
• Experience with cloud security, scalability and CI/CD workflows.

Responsibilities

• Design and develop data pipelines using AWS Step Functions, Lambda, S3, Textract, and Comprehend.
• Build automated document-processing workflows for extracting, transforming, and processing structured and unstructured data.
• Implement document chunking, embeddings, vector indexing, and semantic search.
• Develop and maintain vector databases and knowledge bases to support Retrieval-Augmented Generation (RAG).
• Integrate knowledge bases with AI agents for contextual information retrieval.
• Build AI agents using Claude Agent SDK and deploy them on Amazon Bedrock AgentCore Runtime.
• Develop CI/CD pipelines using GitHub Actions to automate builds, testing, and deployments.
• Optimize data pipelines for scalability, reliability, security, and performance.

Skills

Python

SQL

TypeScript

AWS Step Functions

Lambda

S3

Textract

Comprehend

RAG

Claude Agent SDK

Bedrock

GitHub Actions

Terraform

AWS CDK

AWS IAM

APIs

AgentCore Runtime

Tools

Claude Agent SDK

AgentCore Runtime

GitHub Actions

Terraform

AWS CDK

Job description

Duration: 3+ Months (Extension Possible)

Work Arrangement: Hybrid - 2 days onsite Locals Only

Visa: H1B/ /GC/GC-EAD/H4EAD (Need PP no for travel History) USC

LinkedIn should match the resume dates, projects and should be created before 2021 and have photograph and location mentioned

2 Manager references with LinkedIn

12 years of profile

Experience 10 years Cloud Platform: AWS Primary Language: Python

Key Responsibilities

• Design and develop data pipelines using AWS Step Functions, Lambda, S3, Textract, and Comprehend.
• Build automated document-processing workflows for extracting, transforming, and processing structured and unstructured data.
• Implement document chunking, embeddings, vector indexing, and semantic search.
• Develop and maintain vector databases and knowledge bases to support Retrieval-Augmented Generation (RAG).
• Integrate knowledge bases with AI agents for contextual information retrieval.
• Build AI agents using Claude Agent SDK and deploy them on Amazon Bedrock AgentCore Runtime.
• Develop CI/CD pipelines using GitHub Actions to automate builds, testing, and deployments.
• Optimize data pipelines for scalability, reliability, security, and performance.

Must-have vs. good-to-have skills

Must-have

Good-to-have

Python, SQL

TypeScript

AWS Step Functions, Lambda, S3

AWS Glue

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

GitHub Actions CI/CD

Terraform / AWS CDK

AWS IAM and API integrations

AgentCore Runtime

Important: If this individual must personally build and deploy the Claude agents, move Claude Agent SDK and AgentCore Runtime into the must-have category.

$000,000 – $000,000 Salary range is not shown on the candidate portal