Machine Learning Engineer (AWS | Healthcare | EPIC)

Our client is seeking a skilled Machine Learning Consultant to support the development, tuning, and validation of ML models in a production-grade environment. The ideal candidate will have strong hands-on experience in Python, AWS-based ML workflows, and modern ML frameworks. You will play a key role in building accurate and reliable models while ensuring quality through rigorous evaluation and experimentation tracking. Experiences in Healthcare industry with EPIC is highly desirable. Key Responsibilities • Design, develop, and fine-tune ML models tailored to business requirements. • Rigorously evaluate model performance to identify and rectify errors, ensuring accuracy and consistency across datasets and scenarios. • Implement models using frameworks such as scikit-learn, XGBoost, PyTorch, or TensorFlow. • Track experiments and model versions using MLflow or equivalent tools. • Work in an AWS-based ML infrastructure to access, transform, and use data at scale. • Rigorously test models for accuracy, drift, bias, and performance issues. • Collaborate with cross-functional teams to ensure production-readiness and integration of ML solutions. • Maintain high standards for model quality, explainability, and operational reliability. Required Skills • 3–6 years of hands-on experience in ML model development. • Strong proficiency in Python and related libraries (e.g., Pandas, NumPy, Scikit-learn). • Experience using AWS ML services (e.g., SageMaker, S3, Lambda) in a development or deployment capacity. • Working knowledge of MLflow or similar tools like SageMaker Experiments, DVC, Weights & Biases, etc. • Proven ability to detect, debug, and correct errors or drifts in model behavior or predictions. • Strong understanding of classification, regression, and time-series modeling techniques. • Familiarity with CI/CD best practices for ML and experiment reproducibility. • Experience working with clinical or claims data, preferably from EPIC or other EHR systems. • Understanding of HIPAA compliance and data governance requirements in healthcare ML workflows. Good to Have • Experience with MLOps practices or tools. • Exposure to data versioning, feature stores, or automated model testing frameworks. • Prior work on business-critical ML use cases in domains like finance, retail, healthcare, or manufacturing.