Data Scientist, Interpretable Scoring & ML
Overview
You will design and build the v1 rule-weighted composite scoring logic that turns normalized risk signals into a transparent, defensible score. Working with Python, scikit-learn, and SQL, you will define feature groupings, weights, thresholds, and guardrails. You will partner with data engineering and application teams to productionize scoring logic and establish validation and monitoring approaches. This role offers the chance to shape the architecture for future interpretable ML models while preserving explainability for adjudicator-facing workflows.
What You'll Do8
- 1Build and tune v1 rule-weighted composite scoring logic using normalized inputs from the common risk-signal schema.
- 2Define scoring framework components including feature groupings, weights, thresholds, guardrails, and handling of missing or partial data.
- 3Create interpretable explanations for scores and drivers suitable for adjudicator review, including reason codes and key contributing signals.
- 4Design the scoring architecture to support evolution from rules and weights to interpretable ML models while maintaining auditability.
- 5Prototype and evaluate interpretable model classes and explanation methods such as SHAP-based explanations, constrained or monotonic models, and rule-based hybrids.
- 6Partner with data engineering and application teams to productionize scoring logic, covering data inputs, contracts, output formats, and performance expectations.
- 7Establish validation and monitoring approaches including basic model or score QA, drift indicators, and score distribution checks.
- 8Document scoring methodology, assumptions, and limitations for stakeholder understanding and accreditation or compliance artifacts.
Requirements8
- 1Maintain an active TS/SCI security clearance.
- 2Bachelor's Degree and 8 to 10 years of experience; Master's Degree and 6 to 8 years; PhD and 3 to 5 years (in lieu of Bachelor's, 6 additional years of relevant experience).
- 33-5 years of applied data science experience delivering scoring, ranking, or decision-support models.
- 4Experience implementing interpretable approaches such as rule-based systems, transparent composite scores, or explainability methods including SHAP.
- 5Strong Python skills including scikit-learn and common data science workflows.
- 6Hands-on experience with SQL for data analysis, feature development, and validation.
- 7Ability to communicate scoring logic clearly to technical and non-technical stakeholders, including explaining tradeoffs between accuracy and interpretability.
- 8Familiarity with adjudicative, compliance, fraud, or risk-scoring domains (preferred or bonus).
Salary Insight
$143 - $228k per year
Location
Required Skills
Similar open positions
Explore active roles that match your skills and interests.
CCS INC
VerifiedData Scientist, Predictive Modeling & ML
You will own end-to-end data science projects, from problem framing to Python model deployment in AWS SageMaker. You will collaborate with cross-functional teams, turning raw data into predictive insights that drive business decisions. This role stands out for its focus on production-ready models and modernizing legacy data infrastructure.
Clera
VerifiedData Scientist — Agent Evaluations & Quality
Own the measurement system that determines if our AI executive assistant improves in ambiguous real-world environments. Partner with AI Agent Capabilities engineers to turn hard questions about agent behavior into actionable answers. The role focuses on scaling impact across product surfaces while ensuring quality.
Capital Solutions Group
VerifiedData Scientist / Data Analytics Scientist
Lead data-driven insights to shape business strategy. Own analytical modeling and statistical analysis for large datasets. Drive recommendations through clear communication. Analyze customer base subsets to uncover actionable intelligence. Foster cross-functional collaboration to translate mission needs into technical solutions.
Mercor
VerifiedData Science and Analytics Experts | $60-$70/hr Remote
This remote, hourly role puts your senior data science expertise to work building evaluation tasks that test AI systems against the realities of Fortune 500 enterprise data operations. You'll design realistic scenarios, craft reference outputs, and author scoring rubrics that capture how top analytics leaders think. If you've lived the complexity of enterprise pipelines, governance, and model deployment, this is a chance to shape AI evaluation at the highest level.
Clera
VerifiedData Scientist, Agent Evaluations & Quality
You will own the evaluation and quality measurement systems for Clera's AI agents, which handle email, calendar, and browser automation across diverse business software. As part of a 25-person team, you will define success criteria, build datasets, and design grading pipelines that drive engineering decisions. Working with Python, SQL, and LLM-as-a-judge frameworks, you will calibrate model-based graders and measure false positives, variance, and agreement. This role bridges applied data science and production quality engineering, offering direct impact on agent reliability and user trust.
Mercor
VerifiedData Science Expert | $120-$170/hr Remote
This is a remote, hourly contract role for experienced data scientists who want to shape how AI systems are evaluated. You won't be building models or dashboards yourself — instead, you'll define what great data science work looks like and score AI-generated output against your criteria. The work sits at the intersection of data science and AI evaluation, making it a great fit for someone who enjoys judgment calls and rigorous reasoning. You'll collaborate with a leading AI research organization through Mercor, with pay at $120–$170 per hour.