This role is for a Machine Learning Engineer to design, develop, and implement scalable machine learning models and algorithms. The ideal candidate will collaborate with cross-functional teams to translate business requirements into technical specifications, optimize ML pipelines, and integrate models into existing applications, ensuring compliance with relevant regulations.
Responsibilities
- Design, develop, and implement scalable machine learning models and algorithms to solve complex problems related to claims processing, fraud detection, risk stratification, member engagement, and predictive analytics within the payer landscape.
- Collaborate closely with data scientists, product managers, and other engineering teams to translate business requirements into technical specifications and deliver end-to-end ML solutions.
- Develop and optimize ML model training pipelines, ensuring data quality, feature engineering, and efficient model iteration.
- Conduct rigorous model evaluation, hyperparameter tuning, and performance optimization using statistical analysis and best practices.
- Integrate ML models into existing applications and systems, ensuring seamless deployment and operation.
- Write clean, well-documented, and production-ready code, adhering to high software engineering standards.
- Participate in code reviews, contribute to architectural discussions, and mentor junior engineers.
- Stay abreast of the latest advancements in machine learning, healthcare technology, and industry best practices, actively proposing innovative solutions.
- Ensure all ML solutions comply with relevant healthcare regulations and data privacy standards (e.g., HIPAA).
Skills
Required Technical Skills:
- Programming Language: Expert proficiency in Python.
- Machine Learning Libraries: Strong experience with PyTorch and scikit-learn.
- Version Control: Proficient with Git and GitHub.
- Testing: Solid understanding and experience with Python unittest framework and Pytest for unit, integration, and API testing.
- Deployment: Hands-on experience with Dockerized deployment on AWS or Azure cloud platforms.
- CI/CD: Experience with CI/CD pipelines using AWS CodePipeline or similar alternatives (e.g., Jenkins, GitLab CI).
- Cloud Platforms: Experience with AWS or Azure services relevant to ML workloads (e.g., Sagemaker, EC2, S3, Azure ML, Azure Functions).
