Focus Area
YAML rules schema design (medical_necessity, frequency_limits, coding_intensity), Feature engineering pipelines in Databricks (provider profiles, peer benchmarks, temporal velocity), Rules validation framework (RuleValidator, schema checks), Databricks feature store management (provider_features, peer_benchmarks tables with Z-ordering), Rule performance monitoring (precision, recall, F1 per rule), Snowflake rules deployment (UDFs, stored procedures). Model monitoring (drift detection via Databricks or custom dashboards), CI/CD for Data pipeline and model deployment (automated testing + promotion from staging to production). Feature store integration with models (Databricks Feature Store model serving), Snowflake external function integration with AWS Lambda or Bedrock
Skill
Databricks Certified Associate Data and ML Engineer (preferred), Python 3+ years, Databricks 1+ years (PySpark, Delta Lake, Unity Catalog), Snowflake 3+ years (SQL expert, UDFs, stored procedures), Feature Store (Databricks Feature Store with Z-ordering for fast lookups), Healthcare claims data (CPT, ICD-10, modifiers) expert, YAML rules authoring or validation experience, MLflow experiment tracking (model versioning, A/B testing), SQL (Databricks SQL + Snowflake), Git + GitHub, Must have 3-5 years Databricks + Snowflake production experience, Must have built rule engines or feature pipelines
databricks,snowflake,aws lambda,sql,git,python,healthcare claims,
