Data Scientist

ABC Legal Services•Longmont, CO

3d•$110,000 - $130,000•Onsite

About The Position

Docketly is a fast-growing legal-technology company based in Longmont, Colorado, and a sister company to ABC Legal Services. It helps creditors’ rights firms hire stand-in attorneys through proprietary software and a nationwide attorney network. The Data Scientist builds and operates the machine-learning and analytics systems supporting Docketly’s operations. The role owns production models from initial framing through deployment and monitoring on AWS, develops business intelligence reporting used by leadership and operational and client teams, and supports pricing and margin decisions through financial modeling. The Data Scientist partners with backend engineers on data infrastructure and production issues and can grow into a Senior Data Scientist role by taking ownership of production models and the pricing roadmap. ABC Legal’s data science team provides a resource for consultation on methods.

Requirements

Bachelor’s degree in a related field or equivalent practical experience.
At least 3 years of experience with applied statistics or machine learning.
Knowledge of probability, hypothesis testing, and model evaluation for classification and regression or quantile models, including precision, recall, calibration, quantile coverage, and drift.
At least 3 years of professional SQL and relational database experience.
Python for data analysis and modeling, including pandas, scikit-learn, and a gradient-boosting framework such as XGBoost, LightGBM, or CatBoost.
Experience training and deploying at least one model to production or using a cloud ML platform such as AWS SageMaker.
Experience with Metabase or comparable business-intelligence tooling.
Clear written and verbal communication with non-technical stakeholders.

Nice To Haves

Experience with staged production rollouts, such as canary or phased releases, with holdout comparisons to demonstrate model impact.
Experience with AWS Glue, S3, Lambda, EventBridge, or CloudFormation.
Comfort using AI coding tools such as Claude Code or GitHub Copilot for analysis and modeling work.
Experience diagnosing production database performance issues, including query plans, indexing, and ORM-generated query patterns in a large, high-table-count schema.
Software-engineering practices applied to ML code, such as automated testing with pytest for production pipelines.

Responsibilities

Build and operate production machine-learning models through the full lifecycle, including framing, feature engineering, training, validation, AWS SageMaker deployment, inference infrastructure, and ongoing monitoring.
Build and maintain automated model retraining and drift monitoring.
Conduct staged production rollouts using holdout comparisons to evaluate model impact, and review test designs with the team before launch.
Use AI coding tools to accelerate analysis, modeling, and MLOps work.
Build and maintain the business-intelligence layer and executive reporting on revenue, margin, and volume, including dashboard design and data accuracy.
Perform pricing and margin analysis for client accounts, including ad hoc investigations for strategic accounts, and model the financial impact of proposed pricing changes.
Build and maintain rules-based pricing and case-difficulty logic by court and county, alongside statistical and machine-learning approaches.
Build and tune large scoring and prioritization frameworks in Metabase, including weighting, percentile scenarios, and drop-rate analysis, to support operational decisions such as hearing priority and assignment.
Translate ambiguous business questions into clear, well-scoped analyses.
Partner with engineering on data pipelines using AWS Glue, Lambda, and EventBridge.
Investigate and help resolve production database performance issues, such as ORM query patterns and indexing, in collaboration with backend engineering.
Document methods and decisions in Confluence or an equivalent shared space so other teams can find and build on the work.