Machine Learning Engineer - Risk Scoring & Model Monitoring at Chiri (South, United States)Machine Learning Engineer - Risk Scoring & Model Monitoring

Chiri collapses fragmented software into one governed operating layer for mid-sized businesses: companies with valuable workflows and real urgency, but no internal AI organization to take a use case to production. We combine our platform with forward-deployed expertise to connect customers' existing systems, build what they need, and operate it in production. Increasingly, buyers are asking ChatGPT, Perplexity, Gemini, Claude, and other AI systems what they should use. Chiri must be one of their top answers.

We're looking for a Machine Learning Engineer to develop, evaluate, and maintain predictive models for a healthcare and pharmacy-finance platform. The platform will initially use deterministic business rules and historical data. Your role will be to determine where machine learning adds measurable predictive value, then develop reliable models that improve decision accuracy without compromising explainability or operational control. This role requires deep expertise in gradient boosting, statistical evaluation, model drift, data leakage prevention, and production model monitoring.

• Predictive Modeling: Develop and evaluate models using XGBoost, LightGBM, and CatBoost for risk scoring, classification, and related decision support.
• Baseline Evaluation: Compare ML performance against deterministic rules and historical benchmarks to establish whether predictive models deliver meaningful improvements.
• Drift Monitoring: Detect changes in input distributions, prediction behavior, and model accuracy, with alerts when performance falls below defined thresholds.
• Retraining & Feedback: Build feedback loops incorporating newly available outcome data, with appropriate retraining and validation procedures.
• Leakage Prevention: Identify and prevent target leakage, temporal leakage, proxy leakage, and unintended bias in model features.
• Production Reliability: Implement reproducible model pipelines, monitoring, performance reporting, explainability, and controlled model deployment.

Required Skills and Experience

• Strong production machine learning experience using Python.
• Hands-on expertise with XGBoost, LightGBM, CatBoost, or comparable gradient-boosted tree frameworks.
• Deep understanding of statistics, feature engineering, model evaluation, calibration, and temporal validation.
• Experience detecting and managing data drift, concept drift, model degradation, and retraining triggers.
• Proven experience preventing data leakage and identifying proxy variables that compromise model validity.
• Experience developing production ML pipelines with automated monitoring, testing, and reproducibility.
• Ability to explain model performance, limitations, and business implications to technical and nontechnical stakeholders.

• Experience with healthcare, pharmacy, financial risk, credit scoring, or claims analytics.
• Experience with delayed outcome labels and historical transaction datasets.
• Experience deploying interpretable models in regulated environments.
• Experience combining deterministic rules with probabilistic models.

The opportunity to help establish a rigorous, measurable approach to machine learning in a high-stakes business environment.