Job title: Entry Level Data Scientist - Collections Analytics

Location: Atlanta, GA or Remote

Employment type: Full-time

Reports to: VP Strategic Initiatives

About us

Sequium Asset Solutions is the industry's most progressive and advanced debt collection servicer. Our mission is to provide uncompromising operational excellence by setting the highest standards in service and reliability through the application of our five core values: Leadership, Training, Talent Acquisition, Rewards and Technology. At Sequium, Tomorrow is Today.

We have an outstanding opportunity for an accomplished data scientist to join one of the most exciting and fastest growing companies in the industry. In this role you will report directly to the Vice President of Strategic Initiatives and support analytics and modeling projects across account segmentation, contact strategy optimization, and early-warning

detection. You will work with cross-functional teams (operations, compliance, IT) to turn data into actionable insights, build repeatable analytics, and productionize models. Our company has made huge investments in data science and generated an agentic AI. We are attempting to fully automate all decisioning processes to give us the highest statistical result and incremental value for all performance matrices.

The successful applicant must possess a high level of intelligence, motivation and enthusiasm in creating breakthrough value enhancements. This is a critical position within the organization for someone who is creative, self-starting and who wants to be in control of their own destiny.

Key responsibilities

• Must have significant knowledge using enterprise AI software (Claude, Cursor and Python) with the ability to direct and prompt this software in order to create significant breakthroughs to enhance automated and real-time strategies.
• Build, validate, and maintain predictive models (e.g., credit/payment propensity, churn/risk, contact response) using Python/R and standard ML libraries.
• Clean, explore, and feature-engineer large-structured datasets from multiple sources (payments, contact history, credit bureau, CRM).
• Run A/B tests and propensity-matched experiments to evaluate contact strategies and messaging, measure lift and report results.
• Create dashboards, visualizations, and regular reports for operations and leadership (KPIs: recovery rates, promise-to-pay keep rates, contact conversion, roll rates).
• Assist in productionizing models: packaging, documentation, monitoring, and retraining schedules in collaboration with others.
• Implement and track model performance, fairness, and stability metrics; support model governance and compliance documentation.
• Support data pipelines and ETL tasks; partner with data engineering to ensure data quality and lineage.
• Translate business problems into analytical approaches; present findings and recommended actions to stakeholders.
• Stay current on best practices in supervised/unsupervised learning, causal inference, and responsible AI as applied to collections.

Required qualifications

• Bachelor’s degree (or equivalent) in Data Science, Statistics, Computer Science, Mathematics, Industrial Engineering, or related quantitative field; graduation within the last 2-3 years.
• Solid SQL skills for data extraction and manipulation.
• Strong programming skills in Python.
• Understanding of basic ML algorithms (logistic regression, decision trees, ensemble methods, clustering) and evaluation metrics (precision/recall, confusion matrix, calibration).
• Experience with data visualization tools (Power BI, Tableau or equivalent) or ability to produce clear visual analyses in Python/R.
• Hands-on experience with at least one machine learning project (class project, internship, capstone, or competition) with end-to-end work (data cleaning, modeling, evaluation).
• Strong analytical problem-solving, attention to detail, and ability to communicate technical results to non-technical stakeholders.
• Commitment to ethical data practices and regulatory compliance (willingness to learn collections/consumer protection rules).

Preferred (nice-to-have)

• Internship or part-time experience in finance, collections, payments, credit risk, or customer analytics.
• Familiarity with time-series or survival analysis and propensity scoring.
• Experience with model monitoring frameworks, cloud platforms (AWS, GCP, Azure).
• Knowledge of compliance/regulatory frameworks relevant to collections (e.g., FDCPA basics).

Technical stack expectations

• Data: SQL, relational databases
• Visualization: Power BI
• Languages: Python (R acceptable)
• ML: scikit-learn, XGBoost/LightGBM, basic knowledge of neural nets optional
• Workflow: Git, Jupyter notebooks, basic command line
• Cloud/Infrastructure: AWS/GCP/Azure; containerization (Docker), Kubernetes experience preferred

Success metrics (first 6–12 months)

• Deliver at least one validated predictive model and support its production handoff
• Implement 2–3 dashboards or automated reports used by operations.
• Demonstrate measurable lift from an A/B test or strategy change driven by your analysis.
• Complete formal documentation for at least one model covering training data, features, performance, and monitoring plan.

Behavioral competencies

• Curious, proactive learner who seeks feedback and owns development.
• Team player who collaborates with ops, IT, and compliance.
• Communicates clearly, distills complex analyses into actionable recommendations.
• Comfortable working in a regulated, data-sensitive environment.

Application process

Submit resume, transcript (unofficial acceptable), and a one-page project summary showing relevant work.