Senior Data Scientist / ML

Що робити

Model Development & Deployment: Design, train, evaluate, and deploy machine learning models to predict patient risk scores (e.g., medication refusal, non-compliance, decompensation etc.).
EHR Data Engineering & Processing: Extract, clean, and transform healthcare data from EHR systems (e.g., Credible) to build robust feature sets for predictive modeling.
End-to-End Analytics with Microsoft Fabric: Utilize Microsoft Fabric’s unified analytics platform (including Data Engineering, Data Science, and Real-Time Analytics workloads) to orchestrate data pipelines, manage Lakehouse architectures, and scale ML training/inference.
Clinical Collaboration: Partner closely with clinical stakeholders, medical officers, and care teams to define risk cohorts, ensure the clinical validity of model features, and translate model outputs into actionable clinical workflows.
MLOps & Monitoring: Establish continuous integration, deployment, and monitoring of ML models to track data drift, model degradation, and fairness/bias over time.

Education: Bachelor’s or Master’s degree in Data Science, Computer Science, Statistics, Bioinformatics, Health Informatics, or a related quantitative field.
Professional Experience: 4+ years of experience developing and deploying machine learning solutions in production environments, preferably within healthcare or clinical data ecosystems.
Microsoft Fabric Experience: Hands-on experience building and deploying data and ML workflows within the Microsoft Fabric ecosystem (OneLake, Notebooks, Spark, Data Factory).
Machine Learning Proficiency: Strong grasp of classical machine learning algorithms (e.g., XGBoost, Random Forests, Logistic Regression) and modern deep learning techniques, specifically for tabular and time-series data.
Programming Skills: Advanced proficiency in Python and SQL. Experience with data manipulation and ML libraries (Pandas, PySpark, Scikit-Learn, PyTorch, or TensorFlow).

Cloud Certifications: Relevant Microsoft Azure or Fabric certifications.
Work Environment & Collaboration
Full-time: 8 hours a day.
Schedule: Mon – Fri 9-5 (US EST) overlap with team at least 4 hours.
Team Structure: Work independently on assigned tasks with support from experienced team members.