Job Summary
We are seeking an experienced AWS AI/ML Engineer to support a Medicaid modernization initiative for an HHS client. The ideal candidate will have expertise in Python, Amazon SageMaker, and Synthetic Data Generation techniques to develop AI solutions while ensuring data privacy and regulatory compliance.
Responsibilities
- Develop AI/ML solutions using Python and AWS services.
- Build, train, evaluate, and deploy machine learning models using Amazon SageMaker.
- Design and generate synthetic datasets for healthcare and Medicaid use cases while preserving privacy.
- Prepare, clean, and transform healthcare datasets for model training.
- Collaborate with business analysts, data engineers, and Medicaid SMEs to understand requirements.
- Optimize model performance and monitor production ML workloads.
- Implement MLOps best practices for model deployment and lifecycle management.
- Ensure compliance with HIPAA and healthcare data security standards.
- Document technical designs, model performance, and deployment procedures.
Required Qualifications
- 5+ years of Python development experience.
- 3+ years of AWS cloud experience.
- Hands-on experience with Amazon SageMaker.
- Experience developing machine learning or AI solutions.
- Experience generating or working with synthetic datasets.
- Strong knowledge of data preprocessing, feature engineering, and model evaluation.
- Experience with SQL and data analysis.
- Knowledge of Git and CI/CD pipelines.
Preferred Qualifications
- Experience supporting HHS, Medicaid, Medicare, or healthcare projects.
- Understanding of healthcare claims, member eligibility, provider, or encounter data.
- Experience with AWS Lambda, S3, Glue, Athena, IAM, CloudWatch, and Step Functions.
- Familiarity with Generative AI, LLMs, or Retrieval-Augmented Generation (RAG).
- Knowledge of TensorFlow, PyTorch, or Scikit-learn.
- AWS Certified Machine Learning – Specialty or AWS Certified AI Practitioner.
Technical Skills
Required:
Python
Amazon SageMaker
AWS Cloud
Machine Learning
Synthetic Data Generation
SQL