Machine Learning Engineer

UST is a technology and digital solutions company that partners with organizations on transformation and AI-driven solutions. The company is seeking a Machine Learning Engineer to design, build, validate, and deploy machine learning models for healthcare payer use cases. The role also involves developing Databricks feature engineering pipelines, monitoring production models, protecting sensitive healthcare data, and collaborating with technical and business stakeholders.

Responsibilities:

• Design, build, and validate machine learning models addressing healthcare payer use cases (e.g., claims risk scoring, clinical outcome prediction, provider network analytics, Medicare Advantage risk adjustment)
• Develop and maintain feature engineering pipelines on Databricks, including feature stores, transformations, and reusable feature sets for model training and inference
• Train, tune, and evaluate models using standard ML frameworks, tracking experiments and managing the model lifecycle (versioning, registry, lineage)
• Deploy models to production on Databricks (batch and/or real-time serving), integrating with downstream applications and monitoring systems
• Monitor deployed models for performance, data drift, and degradation, and implement retraining or remediation workflows as needed
• Apply data security and privacy best practices when handling PHI/PII and other sensitive healthcare data, in line with HIPAA and enterprise compliance requirements
• Partner with data engineers, AI/agentic systems developers, product owners, and compliance stakeholders to translate business problems into ML solutions
• Write clean, well-tested, production-quality code and contribute to shared ML tooling, standards, and documentation

Requirements:

• 2–4 years of hands-on experience in machine learning engineering or applied data science, covering the full lifecycle from feature development through model deployment
• Strong proficiency in Python and common ML libraries/frameworks (e.g., scikit-learn, PyTorch, TensorFlow, MLflow)
• Practical experience building, training, and deploying models on Databricks, including feature engineering, experiment tracking, and model serving/deployment on the platform
• Working knowledge of AWS as the underlying cloud infrastructure for data and ML workloads
• Solid understanding of data security fundamentals — encryption, access controls, and secure handling of sensitive data — with comfort operating in a regulated enterprise environment
• Solid software engineering fundamentals: version control, testing, CI/CD, and code review practices
• Strong analytical and communication skills, with the ability to explain model behavior and tradeoffs to both technical and non-technical stakeholders
• Healthcare background is a strong plus — familiarity with claims, clinical, provider, or Medicare Advantage data is valued but not required for strong ML engineering candidates willing to learn the domain
• Databricks Certification (e.g., Databricks Certified Machine Learning Associate/Professional). AWS Certification (e.g., AWS Certified Machine Learning – Specialty, AWS Certified Solutions Architect)
• Prior experience in health insurance, health plans, or another regulated industry, with exposure to HIPAA, SOC 2, or similar compliance frameworks
• Experience with MLOps tooling (MLflow, model registries, CI/CD for ML) and monitoring/observability for production models