AWS Cloud-Native Engineer – Intelligent Document Processing, Data Extraction
Allata
full-time
Posted on:
Location Type: Remote
Location: Remote • Texas • 🇺🇸 United States
Visit company websiteJob Level
Mid-LevelSenior
Tech Stack
AWSCloudDynamoDBTypeScript
About the role
- Build and maintain IDP pipelines leveraging AWS services (Textract, Bedrock, Step Functions, Lambda, S3, DynamoDB).
- Leverage Amazon Bedrock Data Automation to support dynamic extraction logic and structured data generation.
- Develop prompt templates and Bedrock agents for entity recognition, summarization, and structured output generation.
- Automate document classification, metadata extraction, and validation flows using Bedrock model orchestration.
- Manage infrastructure and deployment using AWS CDK (TypeScript).
- Contribute to data automation frameworks for retraining, evaluation, and continuous improvement.
- Integrate with external APIs or data stores for downstream system ingestion.
Requirements
- 5+ years of AWS cloud-native development experience.
- Proficiency with AWS CDK (TypeScript), serverless architecture, and Bedrock LLM APIs.
- Hands-on experience with Intelligent Document Processing, Amazon Textract, and data extraction pipelines.
- Experience extending or customizing AWS IDP Accelerator solutions.
- Familiarity with prompt and context engineering, document vectorization, and data grounding.
- Strong background in automation, data quality validation, and serverless AI workflows.
Benefits
- Health insurance
- Flexible work arrangements
- Professional development opportunities
- Paid time off
Applicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard skills
AWSAWS CDKTypeScriptAmazon TextractBedrockserverless architecturedata extraction pipelinesautomationdata quality validationdocument classification