Data Scientist I – Production Analytics

Codoxo • Duluth, GA

2d

About The Position

Codoxo is hiring a Data Scientist I to support and maintain the statistical detection, scoring, and reporting analytics running in production across its healthcare payment integrity products. The role begins with recurring work such as configuring clients, validating scheduled reports, and investigating issues with support from senior data scientists. As familiarity with the systems grows, the position takes on more independent responsibility for production analytics and contributions to the production codebase.

The role offers hands-on experience with healthcare claims data, statistical methodology, and a large Python codebase. It includes maintaining analytics and client configurations, improving reliability and validation, contributing code and tests through review and CI, and investigating the quality of existing detectors and scoring logic. The position collaborates with Data Science, Customer Success, Data Engineering, Platform Engineering, and Product, and may grow to include designing and evaluating new statistical detectors and contributing to product capabilities and research problems.

Work is performed in an office environment, either in the company office or from home. Remote employees must have a stable high-speed internet connection, measured using a speed test on the company-issued laptop. The work requires using a computer and standard office equipment while working at a desk.

Requirements

• Bachelor’s degree in Data Science, Statistics, Mathematics, Computer Science, or a related quantitative field.
• 0–2 years of experience in data science, analytics, data engineering, or software engineering; strong internships and academic projects count.
• Working proficiency in Python and SQL, and confidence reading code written by others.
• Familiarity with git and the basics of code review and testing.
• Foundational knowledge of statistics, including distributions, variability, and distinguishing signal from noise.
• Strong debugging instincts and willingness to investigate unexpected results across data, code, configuration, and workflow.
• Strong attention to detail, particularly because outputs reach clients.
• Ability to keep several recurring deliverables on schedule.
• Clear written communication and judgment about when to continue investigating and when to ask for help.
• Curiosity about complex healthcare data and willingness to learn the payment integrity domain.
• Remote workers must have stable high-speed internet, with performance measured on the company-issued CODOXO laptop.
• Ability to work on a computer, operate standard office equipment, and work at a desk in an office or home-office environment.

Nice To Haves

• Experience with healthcare claims data or healthcare analytics, and coding systems such as ICD-10, CPT, or HCPCS.
• Experience with pandas, NumPy, or comparable Python data libraries.
• Exposure to production data pipelines or scheduled workflows such as Airflow.
• Experience with AWS or another major cloud platform, Spark, or other distributed processing.
• Experience with SQL-based data warehouses and query performance tuning.
• Practical experience with statistical testing, regression, anomaly detection, or clustering.
• Awareness of security or compliance requirements in regulated environments, such as HIPAA, FedRAMP, or SOC 2.
• Familiarity with machine learning concepts and model evaluation.

Responsibilities

• Configure new clients to use analytical workflows and reports included in their purchased solutions, and maintain configurations as client needs change.
• Validate monthly and quarterly reporting cadences, confirming jobs run on schedule and outputs are accurate and complete before delivery.
• Investigate failures and unexpected results, resolve them or escalate with a clear account of findings.
• Support client-specific requests for claims examples, analytical validation, and supporting data.
• Automate recurring manual steps, add validation checks, and document configurations, known issues, and resolutions.
• Contribute to production analytics code changes needed for security, compliance, and ongoing support, initially partnering with senior data scientists and engineers.
• Read and trace workflows in the existing Python codebase and identify all affected uses of code patterns.
• Write and update unit tests, participate in code review and CI, and validate changes in a development environment before production deployment.
• Assess how code changes behave in production, including in long-running jobs, at large client data volumes, and on client-specific paths.
• Work with Data Engineering and Platform Engineering on data quality, pipeline, and infrastructure issues.
• Monitor the output quality of production statistical detectors and scoring logic.
• Investigate noisy, low-value, or unexpected detector behavior by analyzing claims and flagged entities and identifying data quality, configuration, parameter, or statistical logic causes.
• Make well-scoped detector fixes, such as adjusting parameters, thresholds, or configuration, and validate whether output improves.
• Bring recommendations for broader statistical methodology changes to senior data scientists and collaborate on design and validation.
• Document detector changes, expected impact, and validation evidence, and flag detectors that may need reworking, replacement, or retirement.
• Collaborate with Data Science, Customer Success, Data Engineering, Platform Engineering, and Product.
• Translate client and Customer Success feedback into analytical or technical changes.
• Communicate root cause, client impact, resolution, and recurrence-prevention needs clearly.
• Help develop processes that support analytics as the client base grows.

Benefits

• Health, dental, and vision insurance with 100% employee premium coverage starting Day 1.
• Unlimited PTO.
• Annual professional development stipend.
• Annual home office stipend.
• 401(k) match after 90 days.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level