AI/ML Document Processing Developer
M9 Solutions2 hours ago
Remote, United StatesSenior
Base Salary
$115k - $130k/yr
Responsibilities
- Build and operate backend services and batch pipelines that classify and extract data from high-volume document sets using AWS Bedrock.
- Own end-to-end document processing pipelines covering S3 ingestion, multi-format parsing, LLM and rules-based classification, OCR fallback, and accuracy, cost, and throughput tooling.
- Build AI unstructured-data document scanning pipelines for healthcare provider and health insurance files.
- Extract key data elements for business logic and data validation, and convert scanning results into structured business data.
- Develop RESTful services and event-driven backends in AWS using Python and concurrent processing for high-throughput workloads.
- Implement document and text processing for PDF, DOCX, and email formats, including OCR fallback.
- Measure and improve model output quality using ground-truth datasets, precision and recall, A/B comparisons, and prompt iteration based on error analysis.
- Handle PII and PHI using appropriate isolation, encryption, IAM, and audit controls.
- Provide technical assistance and end-user troubleshooting for bugs, enhancements, and how-to requests.
- Coordinate across multiple projects and business and technical stakeholders.
Requirements
- Active Public Trust security clearance is required.
- Bachelor's degree or higher is required.
- At least 5 years of experience developing RESTful services and event-driven backends in AWS is required.
- Hands-on experience with AWS Bedrock or comparable LLM platforms, including prompt engineering, structured output, model selection, and token and cost management, is required.
- Experience with AWS S3, Lambda, Fargate or Batch, ECR, IAM, KMS, and CloudWatch is required.
- Strong Python skills, including concurrent processing for high-throughput batch workloads, are required.
- Experience processing PDF, DOCX, and email formats and using OCR tools such as Textract or Tesseract is required.
- Experience with relational and NoSQL databases such as Postgres and DynamoDB, plus Redis caching, is required.
- Experience building Docker images and deploying through CI/CD tools such as Git, Jenkins, or GitHub Actions is required.
- Experience with pytest or equivalent unit testing and code coverage tools is required.
- Experience with agile development tools including JIRA is required.
- Strong communication, multitasking, troubleshooting, and stakeholder-management skills are required.
- Preferred qualifications include healthcare or federal health agency experience, model-quality improvement, hybrid rules and LLM architectures, regulated document workflows, Salesforce integration, Snowflake or Redshift analytics, Terraform, CDK, CloudFormation, and active AWS certifications.
Benefits
- Full-time employee position with M9 Solutions benefits available.
- Fully remote work supporting a client and government contract located in Washington, DC.
- Listed base salary range of $115,000 to $130,000 USD.
- The employer states that it values diverse perspectives and offers a competitive compensation package.
Tech Stack
Amazon DynamoDBAmazon RedshiftDockerGitGitHub ActionsJenkinsPostgreSQLpytestPythonRedisSnowflakeTerraform
Categories
About M9 Solutions
M9 Solutions provides IT services and staffing for U.S. federal agencies, including software development, cloud migration, cybersecurity, data delivery and analytics, and applications and infrastructure support. The privately held firm, founded in 2007 and headquartered in Vienna, Virginia, delivers cleared talent and project-based solutions and has supported more than 30 federal agencies, plus some commercial customers.