AI/ML Document Processing Engineer

Piper Companies; United States; Remote; USD 146,000 - 158,000; Full time

Benefits offered by this job

Health insurance

Paid time off

401(k)

Job summary

Piper Companies seeks an experienced AI/ML Document Processing Developer to design and implement document ingestion pipelines in AWS. The role focuses on turning unstructured healthcare documents into structured data using OCR, LLMs, and AI-powered processing.

You will build RESTful services, work in an Agile environment, and collaborate with stakeholders to ensure secure, scalable, high-throughput data pipelines. Healthcare domain experience is a plus.

Qualifications

• 5+ years creating RESTful services and event-driven backends in AWS.
• Hands-on with AWS Bedrock or comparable LLM platforms.
• Experience with S3, Lambda, ECS/Fargate or Batch, ECR, IAM, KMS, CloudWatch.
• Strong Python development experience, including concurrency.
• Experience with OCR and document processing tech.
• RDBMS and NoSQL like PostgreSQL and DynamoDB.
• Redis or similar caching systems.

Responsibilities

• Design and build AI-powered document processing pipelines for unstructured data.
• Process healthcare documents across PDFs, DOCX, emails, and scans.
• Extract, validate, and transform data from unstructured content.
• Build RESTful APIs and event-driven services in AWS.
• Develop scalable data processing pipelines using Python.
• Implement OCR and extraction using AWS Textract, Tesseract, etc.
• Integrate structured outputs into downstream systems and reporting tools.
• Collaborate in Agile teams with stakeholders and manage production fixes.

Skills

RESTful services

Event-driven backends

AWS

Python

OCR / document processing

LLMs / Bedrock

PostgreSQL / DynamoDB

Docker

CI/CD

pytest

JIRA/Agile

Security & HIPAA

Tools

AWS Textract

Tesseract

GitHub Actions

Terraform

CloudFormation

AWS CDK

Snowflake

Redshift

Job description

Piper Companies seeks an experienced AI/ML Document Processing Developer to design and implement document ingestion pipelines in AWS. The role focuses on turning unstructured healthcare documents into structured data using OCR, LLMs, and AI-powered processing.

You will build RESTful services, work in an Agile environment, and collaborate with stakeholders to ensure secure, scalable, high-throughput data pipelines. Healthcare domain experience is a plus.