Principal Data Scientist - Identity and Matching Models
J
JobgetherIdentity resolution
Candidates must be based in one of the following eligible US states: Arizona, California, Colorado, Florida, Georgia, Kentucky, Maryland, Michigan, Missouri, New Jersey, Nevada, North Carolina, Pennsylvania, South Carolina, South Dakota, Texas, Virginia, Washington, or Wyoming.Full-TimePrincipal
Salary$166,500–$216,000, depending on factors such as experience, skills, job level, and market conditions.
Apply NowOpens the employer's application page
Job Details
- Experience
- At least 6 years of experience in applied data science
- Required Skills
- PythonSQLMachine LearningMLFlowSparkDatabricks
Requirements
- At least 6 years of experience in applied data science, with demonstrated results developing and delivering models into production.
- A bachelor's degree in a quantitative discipline is expected; a master's degree is preferred. Equivalent professional experience may be considered.
- Experience taking models from research through cloud-based production deployment, monitoring, and post-launch performance evaluation.
- Strong Python and SQL skills.
- Experience using Spark or similar distributed computing technologies to process very large datasets, including datasets with 100 million or more rows.
- Practical experience with AWS SageMaker, Databricks, MLflow, or comparable platforms for model development, deployment, tracking, and monitoring.
- Ability to evaluate model quality when reliable ground-truth labels are limited, using sampling, manual review, and statistically informed accuracy and confidence estimates.
- Ability to distinguish meaningful improvements from statistical noise and explain model performance, limitations, uncertainty, and trade-offs.
- Experience monitoring data changes, identifying model or label degradation, maintaining retraining processes, and documenting workflows for reproducibility.
- Understanding of appropriate personal-data handling, including opt-out rules, data retention requirements, and data lineage practices.
- Experience in record linkage, entity resolution, deduplication, graph-based methods, AI-assisted data labeling, or converting raw model scores into actionable confidence measures is preferred.
Responsibilities
- Design, train, test, and deploy identity and record-matching models that determine whether records refer to the same individual and quantify matching confidence.
- Develop labeling strategies and evaluation datasets, conduct manual quality checks, and estimate model accuracy when comprehensive ground-truth data is unavailable.
- Use AI models to support large-scale data labeling and validate their outputs against human judgment.
- Collaborate with machine learning engineering and DevOps teams to deploy models on AWS and maintain retraining schedules, model registries, version tracking, and data lineage.
- Review data pipelines and model outputs before release, identify changes and regressions, and investigate performance shifts.
- Communicate model findings, limitations, and performance to technical and business stakeholders.
- Partner with product owners to turn analytical findings into user stories, measurable targets, and prioritized research initiatives.
- Monitor changing data distributions, identify outdated models and labels, and establish refresh processes.
- Review code, document research and modeling decisions, share knowledge, and contribute to data science and machine learning working groups.
- Ensure models and data workflows comply with opt-out requirements, retention policies, and data lineage standards.
View Full Description & ApplyYou'll be redirected to the employer's site
