AWS Cloud-Native Engineer (Intelligent Document Processing / Data Extraction)

We’re hiring a Cloud-Native Engineer to lead the development of a serverless Intelligent Document Processing (IDP) platform using AWS Bedrock and Bedrock Data Automation. The role focuses on scalable document extraction, classification, and data automation across unstructured inputs. Responsibilities include building and maintaining IDP pipelines leveraging AWS services (Textract, Bedrock, Step Functions, Lambda, S3, DynamoDB), leveraging Amazon Bedrock Data Automation to support dynamic extraction logic and structured data generation, developing prompt templates and Bedrock agents for entity recognition, summarization, and structured output generation, and automating document classification, metadata extraction, and validation flows using Bedrock model orchestration. The candidate will manage infrastructure and deployment using AWS CDK (TypeScript) and contribute to data automation frameworks for retraining, evaluation, and continuous improvement, as well as integrate with external APIs or data stores for downstream system ingestion.