Required Skills & Experience
- Experience with ML engineering, MLOps, data engineering, or a related role, with experience taking models to production
- Git/GitHub experience
- Hands-on use of AI coding agents such as Claude Code or Cortex Code
- Strong Python and SQL, with a track record of production-quality code
- Hands-on experience with Snowflake and cloud data environments
- Snowflake ML experience: Snowpark, Model Registry, Tasks/DAGs, or Snowpark Container Services, Feature store, Experiments, ML Jobs
- Experience with MLOps practices: model versioning, automated testing, deployment, monitoring, and lifecycle management
- Experience with Git-based development, CI/CD, and environment/dependency management
- Experience with predictive analytics, statistical modeling, and model performance evaluation
- Experience presenting technical results to non-technical stakeholders in a way that informed a decision
- Bachelor’s or Master’s degree in Computer Science, Engineering, Mathematics, Statistics, Data Science, or a related field, or equivalent practical experience
Nice to Have Skills & Experience
- Experience with Google Cloud Platform
- Familiarity with ML governance, drift monitoring, lineage, and reproducible model evaluation
- Implement RBAC, security, and PHI controls that meet our governance and HIPAA requirements
- Experience with Medicare Stars, Medicare Advantage, HEDIS, or healthcare quality analytics
- Experience with large-scale healthcare or payer data
- R experience, including statistical modeling packages
Job Description
Insight Global is seeking a senior hands-on ML Engineer/MLOps Engineer with strong production Snowflake experience. This is not a traditional Data Scientist role. The resource will take existing Python/R statistical and ML models and productionize them within a Snowflake environment, including ML pipeline automation, deployment, monitoring, model drift, troubleshooting, and ongoing lifecycle management.
Responsibilities:
MLOps and production engineering:
- Productionize the ML lifecycle in Snowflake, from experimentation to deployment, so data scientists can ship models without rebuilding them.
- Build data and feature pipelines that give the Stars team trusted, regularly refreshed inputs for predictive models.
- Deploy and manage Python and R models, including versioning, lineage, champion/challenger testing, and promotion.
- Orchestrate and automate Snowflake ML workflows using Tasks/DAGs and related tooling.
- Build Git-based CI/CD and automated testing so releases are repeatable and safe.
- Monitor production models for drift, calibration, lift, and leakage, and act on what you find.
AI-assisted development:
- Use Cortex Code, Claude Code, and similar AI coding agents to develop, refactor, test, debug, and document Python, R, SQL, and pipeline code.
- Create prompts, agent skills and plugins, project context, and coding standards so the broader data science team can use AI tools consistently and safely.
Analytics partnership:
- Support data scientists, analysts, and business stakeholders on predictive analytics, prospective studies, ROI assessments, and clinical program evaluation.
- You support the data science team’s work and ensure it is reproducible
- Analyze large structured and unstructured healthcare datasets and produce reproducible outputs.
Production support and communication:
- Troubleshoot authentication, package and dependency, model convergence, and pipeline issues.
- Explain technical solutions, findings, risks, and recommendations to technical, business, and executive audiences.