Cleared AI/ML Data Document Processing Developer - 173227

Zachary Piper Solutions; Northern (KY); Hybrid; USD 146,000 - 158,000; Full time

Job summary

Zachary Piper Solutions is seeking an experienced AI/ML Document Processing Developer to design, build, and enhance document ingestion and processing solutions that leverage Artificial Intelligence, Machine Learning, and Large Language Models (LLMs). This role will focus on transforming unstructured documents into structured, actionable data that supports business processes and validation workflows.

Responsibilities include designing AI-powered pipelines, processing healthcare-related documents,

Qualifications

• 5+ years RESTful services and AWS experience.
• Hands-on with AWS Bedrock or similar LLM platforms (prompt engineering, structured outputs, model selection).
• Production AWS experience: S3, Lambda, ECS/Fargate or Batch, ECR, IAM, KMS, CloudWatch.
• Strong Python development, including concurrent processing for high-volume workloads.
• Experience with document processing and OCR technologies.

Responsibilities

• Design and build AI-powered document processing pipelines for unstructured data.
• Process healthcare-related documents across PDFs, DOCX, emails, and scanned files.
• Extract, validate, and transform data from unstructured content.
• Build RESTful APIs and event-driven backends in AWS.
• Develop scalable Python-based data processing solutions.
• Implement OCR and extraction using AWS Textract, Tesseract or equivalent.
• Integrate outputs into downstream apps and databases.
• Collaborate in Agile teams and support platform improvements.

Skills

RESTful services

Event-driven backends

AWS Bedrock

Python

OCR/Document processing

PostgreSQL

DynamoDB

Redis

Docker

CI/CD

JIRA

pytest

Agile/Scrum

Tools

AWS S3

Lambda

ECS/Fargate

ECR

IAM

KMS

CloudWatch

GitHub Actions

Jenkins

Docker

Terraform

CloudFormation

AWS CDK

Job description

AI/ML Document Processing Developer

Locations: Connecticut, Delaware, Florida, Georgia, Indiana, Kentucky, Maine, Maryland, Massachusetts, Michigan, New Hampshire, New Jersey, New York, North Carolina, Ohio, Pennsylvania, Rhode Island, South Carolina, Tennessee, Vermont, Virginia, West Virginia, District of Columbia.

Overview

Zachary Piper is seeking an experienced AI/ML Document Processing Developer to design, build, and enhance document ingestion and processing solutions that leverage Artificial Intelligence, Machine Learning, and Large Language Models (LLMs). This role will focus on transforming unstructured documents into structured, actionable data that supports business processes and validation workflows.

Responsibilities

• Design and develop AI-powered document processing pipelines for unstructured data.
• Process healthcare-related documents across multiple formats, including PDFs, DOCX files, emails, and scanned documents.
• Extract, validate, and transform critical business data from unstructured content.
• Build and maintain RESTful APIs and event-driven backend services in AWS.
• Develop scalable, high-throughput data processing solutions using Python.
• Implement OCR and document extraction capabilities using tools such as AWS Textract, Tesseract, or similar technologies.
• Integrate structured output into downstream applications, databases, and reporting environments.
• Participate in Agile development processes and collaborate with technical and business stakeholders.
• Troubleshoot production issues, implement enhancements, and support ongoing platform improvements.
• Ensure security, scalability, and operational excellence across cloud-based solutions.

Required Qualifications

• 5+ years of experience developing RESTful services and event-driven backend applications in AWS.
• Hands-on experience with AWS Bedrock or comparable LLM platforms, including:
  • Prompt engineering
  • Structured outputs
  • Model selection
  • Token and cost optimization
• Strong AWS experience in production environments, including:
  • S3
  • Lambda
  • ECS/Fargate or AWS Batch
  • ECR
  • IAM
  • KMS
  • CloudWatch
• Strong Python development experience, including concurrent processing for high-volume workloads.
• Experience with document and text processing technologies, including OCR solutions.
• Experience with relational and NoSQL databases such as PostgreSQL and DynamoDB.
• Experience with Redis or similar caching technologies.
• Experience building and deploying containerized applications using Docker.
• Experience with CI/CD tools such as GitHub Actions, Jenkins, or Git.
• Experience with automated testing frameworks such as pytest.
• Experience working in Agile environments utilizing JIRA.
• Strong communication and collaboration skills.

Preferred Qualifications

• Healthcare, health insurance, or regulated industry experience.
• Experience with CMS-related projects and healthcare document workflows.
• Experience measuring and improving LLM/model performance through prompt optimization, precision/recall analysis, A/B testing, and error analysis.
• Experience designing hybrid AI architectures that combine deterministic business rules with LLM-based processing.
• Experience handling PII/PHI in HIPAA-compliant environments.
• Experience integrating data with Salesforce.
• Experience with Snowflake, Redshift, or similar analytics platforms.
• Experience with Infrastructure as Code tools such as Terraform, AWS CDK, or CloudFormation.
• Active AWS certification(s).

Clearance Requirement

• Ability to obtain and maintain a CMS T4 Public Trust clearance.

Non-Negotiable Requirements

• 5+ years of experience developing RESTful services and event-driven backends in AWS.
• Hands-on experience with AWS Bedrock or comparable LLM platforms.
• Production experience with AWS services including S3, Lambda, ECS/Fargate or Batch, ECR, IAM, KMS, and CloudWatch.
• Strong Python development experience.
• Experience building document processing and extraction solutions using AI/ML technologies.

Compensation:

• Salary: $146,000 - $158,000
• Benifit: Benefits: PTO, Paid Holidays, Medical, Dental, Vision, 401(k), Sick Leave (as required by law)

Keywords:

AI/ML, Machine Learning, Artificial Intelligence, AWS, Amazon Web Services, AWS Bedrock, Large Language Models, LLM, Prompt Engineering, Generative AI, REST API, RESTful Services, Event-Driven Architecture, Event-Driven Backends, Python, S3, Lambda, AWS Lambda, ECS, Fargate, AWS Batch, ECR, IAM, KMS, CloudWatch, Document Processing, Intelligent Document Processing, OCR, Optical Character Recognition, AWS Textract, Tesseract, PDF Processing, DOCX Processing, Email Processing, Unstructured Data, Structured Data Extraction, Data Validation, Data Pipelines, Backend Development, API Development, Microservices, PostgreSQL, Postgres, DynamoDB, NoSQL, Relational Databases, Redis, Docker, Containerization, CI/CD, Git, GitHub Actions, Jenkins, Pytest, Automated Testing, Unit Testing, Agile, Scrum, JIRA, Healthcare, Health Insurance, Claims Processing, CMS, Medicare, Medicaid, HIPAA, PHI, PII, Healthcare Documents, Data Integration, Salesforce, Snowflake, Redshift, Terraform, CloudFormation, AWS CDK, Infrastructure as Code, IaC, Batch Processing, Concurrent Processing, High-Throughput Systems, Model Evaluation, Precision Recall, A/B Testing, Prompt Optimization, Error Analysis, Token Management, Cost Optimization, Hybrid AI Architecture, Production Support, Troubleshooting, Cloud Security, VPC, Encryption, Least Privilege Access, Audit Logging, Public Trust Clearance