Note: The job is a remote job and is open to candidates in USA. Cleartelligence is seeking an AI/ML Engineering Lead to design and deliver advanced machine learning and predictive analytics solutions, primarily on the Snowflake platform. The role leads end-to-end predictive model development, production deployment, scenario forecasting, stakeholder communication, and mentoring across client engagements.
Responsibilities
- Lead the end-to-end design of predictive machine learning solutions, from hypothesis-driven feature identification through model deployment and monitoring
- Partner with Data Engineering teams to define, validate, and cleanse the feature pipeline, ensuring proper handling of anomalous data and confirming that all features are knowable at the time of prediction
- Design a longevity approach that will combine entity-level segmentation to enable risk and scenario forecasting
- Evaluate, select, and apply appropriate algorithms and frameworks
- Train and test model/feature combinations, calculating accuracy and fit measures (e.g., SMAPE, RMSE, correlation) to identify the best-performing approach and avoid well-fitting but poorly generalizing models
- Derive confidence bands and best-case/worst-case ranges from model fit to communicate prediction uncertainty to business stakeholders
- Translate model outputs into operational and financial insights, including risk forecasts by segment, key contributing factors, and recommended operational levers, for delivery through BI dashboards such as Tableau
- Collaborate with Solution Architecture, Data Engineering, Analytics and development teams to operationalize models into scalable, production-ready pipelines and reporting tools/agentic workflows
- Support “what-if” and scenario-planning capabilities that allow clients to model the impact of changes in population mix, referral patterns, or other operational variables
- Communicate directly with client stakeholders, including executive, financial, and operational leadership, to gather requirements, present findings, and drive adoption of predictive insights
- Identify and mitigate model risk, including data completeness issues, rare-event uncertainty, and confounding variables, using techniques such as ensemble modeling and rigorous back-testing
- Establish and champion ML best practices, reusable frameworks, and thorough documentation to support long-term scalability and knowledge transfer
- Provide input into project scoping, level-of-effort estimates, and staffing plans for machine learning engagements
- Mentor and provide technical guidance to data scientists and ML developers supporting the engagement
Skills
- Bachelor's or Master's degree in Computer Science, Data Science, Statistics, Applied Mathematics, or a related field
- 5+ years of hands-on experience building, validating, and deploying machine learning models in production environments; consulting or client-facing project experience strongly preferred
- Deep proficiency in **Python** and core ML libraries (scikit-learn, **XGBoost**, LightGBM, CatBoost)
- Experience with survival/time-to-event analysis and/or time-series foundation models strongly preferred
- Experience with cloud data platforms, particularly **Snowflake** (including Snowflake-native ML/Snowpark workflows); familiarity with AWS or Azure a plus
- Strong understanding of feature engineering, model evaluation methodology (SMAPE, RMSE, correlation), and uncertainty quantification
- Experience partnering with BI/visualization teams (e.g., Tableau) to operationalize model outputs into stakeholder-ready dashboards
- Strong customer-facing communication and presentation skills, with the ability to translate complex modeling concepts for non-technical, executive audiences (e.g., CFO, operations leadership)
- Demonstrated ability to lead a project workstream, including scoping, timeline estimation, and mentoring junior team members
- Ability to work across multiple client engagements and with teams across geographical regions
- Prior experience in **healthcare** (Medicare specifically), insurance, or another regulated, data-intensive industry a plus
- Working knowledge of data governance and regulatory considerations (e.g., HIPAA) a plus
- Ability to work EST hours
- Consulting or client-facing project experience strongly preferred
- Experience with survival/time-to-event analysis and/or time-series foundation models strongly preferred
Company Overview