Remote AI/ML Document Processing Engineer

Piper Companies; United States; Remote; USD 120,000 - 160,000; Full time

Benefits offered by this job

Health insurance

401K

PTO

Sick Leave

Holidays

Job summary

Piper Companies is seeking an AI/ML Document Processing Developer to build and support AI-driven pipelines for a CMS program, focusing on extracting structured data from high-volume healthcare and insurance documents using AWS and Generative AI.

You will design ingestion and classification systems, integrate with AWS services, and optimize outputs, throughput, and costs while maintaining HIPAA-compliant handling of PHI.

Qualifications

• 5+ years developing RESTful services and event-driven backends in AWS.
• Strong Python development experience.
• Hands-on AWS Bedrock or comparable LLM platform experience.
• Experience with prompt engineering, structured outputs, model selection, and token/cost optimization.
• Production AWS experience with: S3, Lambda, ECS/Fargate or AWS Batch, ECR, IAM, KMS, CloudWatch.
• Experience building and supporting document-processing pipelines.
• OCR experience using Textract, Tesseract, or similar technologies.
• Experience processing PDFs, DOCX files, email formats, and other unstructured documents.
• Experience with Postgres, DynamoDB, and Redis.
• Docker and CI/CD experience using GitHub Actions, Jenkins, or similar tools.
• Automated testing experience using pytest or equivalent.

Responsibilities

• Build AI-powered document ingestion and classification pipelines.
• Process healthcare provider and health insurance documents across multiple formats.
• Extract key business data from unstructured content.
• Convert document-processing results into structured data for downstream business workflows and develop and maintain AWS-based backend services and batch-processing pipelines.
• Improve output quality, throughput, and cost efficiency of AI processing solutions.

Skills

RESTful services

Python development

AWS Bedrock

Prompt engineering

Model selection

Token/cost optimization

S3

Lambda

ECS/Fargate

AWS Batch

ECR

IAM

KMS

CloudWatch

Textract

Tesseract

Postgres

DynamoDB

Redis

Docker

CI/CD

GitHub Actions

Jenkins

pytest

Tools

AWS Bedrock

Textract

Tesseract

Postgres

DynamoDB

Redis

Docker

GitHub Actions

Jenkins

pytest

Job description

Piper Companies is seeking an AI/ML Document Processing Developer to build and support AI-driven pipelines for a CMS program, focusing on extracting structured data from high-volume healthcare and insurance documents using AWS and Generative AI.

You will design ingestion and classification systems, integrate with AWS services, and optimize outputs, throughput, and costs while maintaining HIPAA-compliant handling of PHI.