Lead Data Scientist

paretocaptiveservicesllc; United States; Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Fully paid medical, dental, and vision

Flexible PTO

401k company contribution

Tuition reimbursement

Professional development allowance

Transportation allowance and parking

Hybrid work environment

Job summary

Pareto Captive Services LLC is seeking a Senior data science professional to lead applied AI and data science workstreams in healthcare and underwriting. You will own end-to-end model delivery, partner with analytics, business and engineering to translate evidence into actions and outcomes.

The role emphasizes production-grade models, explainability, and governance, with a focus on pricing accuracy, risk selection, and operational efficiency. A hybrid work setup is offered.

Qualifications

• Bachelor's or master's in a quantitative field (Statistics/Data Science/CS/Math/Engineering).
• 8+ years in data science, ML, statistics, or actuarial analytics, with healthcare/insurance data experience.
• Proficiency in Python and SQL, with ML frameworks like scikit-learn, XGBoost, or GBMs.
• Deep expertise in supervised/unsupervised ML, explainability, calibration, and optimization.
• Ownership of production models and the MLOps lifecycle on AWS or similar cloud platform.

Responsibilities

• Own end-to-end delivery of predictive underwriting and pricing workstreams from framing to deployment, monitoring, and iteration.
• Frame evidence-based recommendations across model quality, risk, cost, and scalability.
• Define Analytics-Ready DataSet and reusable feature requirements across claims, pharmacy, utilization, financial, underwriting, and external data.
• Apply point-in-time development and out-of-time validation for claims maturity, seasonality, leakage, stability, and uncertainty.
• Develop, compare, and challenge predictive models and hybrid rule/model approaches.
• Balance near-term delivery with exploration of emerging methods including deep learning or generative AI.
• Translate model needs into detailed feature requirements and coordinate with legal for approvals.
• Manage third-party model evaluations and ROI analyses when independent validation is needed.
• Produce explainable, reproducible outputs and follow governance standards.

Skills

Advanced Python & SQL

Explainable ML & model validation

Stakeholder communication

Education

Bachelor's or Master's in Statistics/Data Science/CS/Math/Engineering

Tools

scikit-learn

XGBoost

GBMs

AWS / MLOps

PyTorch

Job description

Role overview

Senior individual contributor role leading applied AI and data science workstreams that turn healthcare and underwriting data into measurable improvements in risk selection, pricing accuracy, operational efficiency, and the underwriting experience. The position owns end-to-end model delivery and partners across business, analytics, and engineering to translate complex evidence into clear recommendations and business outcomes.

Responsibilities

• Own end-to-end delivery of predictive underwriting and pricing workstreams, from problem framing through deployment, monitoring, and continuous improvement
• Frame evidence-based recommendations and trade-offs across model quality, risk, cost, and scalability
• Define Analytics-Ready Dataset and reusable feature requirements across claims, pharmacy, utilization, financial, underwriting, and external data
• Apply point-in-time development and out-of-time validation for claims maturity, seasonality, leakage, stability, and uncertainty
• Develop, compare, and challenge predictive models, distributions, and hybrid rule/model approaches
• Balance near-term delivery with disciplined exploration of emerging methods, including deep learning or generative AI solutions
• Translate model needs into detailed feature requirements and partner with legal for approvals
• Manage third-party model evaluations and ROI analyses when independent validation is needed
• Produce explainable, reproducible outputs and follow shared documentation, testing, monitoring, and governance standards

Requirements

• Bachelor's or master's degree in Statistics, Data Science, Computer Science, Mathematics, Engineering, or a related quantitative field
• 8+ years in data science, ML, statistics, or actuarial analytics, including substantial work with healthcare, pharmacy, insurance risk, or sensitive longitudinal data
• Advanced Python and SQL, with experience in scikit-learn, XGBoost, GBMs, or comparable frameworks
• Deep expertise in supervised and unsupervised ML, explainability, statistical distributions, rare-event modeling, calibration, and optimization
• Proven ownership of production models and the MLOps lifecycle on AWS or comparable cloud platform, including version control, testing, deployment, monitoring, retraining, rollback, and documentation
• Strong business acumen and ability to connect analytical outputs to measurable outcomes and trade-offs

Nice to have

• PySpark or comparable distributed-computing experience
• PyTorch experience
• Familiarity with Kedro or similar pipeline frameworks
• Experience with LLMs, prompt engineering, RAG, embeddings, vector databases, or agentic frameworks

Benefits and work setup

• Fully paid medical, dental, and vision benefits
• Flexible PTO
• 401k company contribution
• Tuition reimbursement
• Professional development allowance
• Transportation allowance and daily parking reimbursement
• Engaging hybrid work environment