Machine Learning Engineer

Central Insurance•Alpharetta, GA

2d•Hybrid

About The Position

Central Insurance is a family-owned property and casualty insurance group operating since 1876. The Machine Learning Engineer partners with actuaries, data scientists, software engineers, data engineers, and business stakeholders to design, deploy, and support machine learning solutions. The role focuses on transitioning models from experimentation into reliable, scalable, maintainable, production-ready applications, services, and decision-support workflows aligned with business objectives. The engineer develops and maintains deployment processes, APIs and scoring workflows, pricing data pipelines, model monitoring and observability practices, and MLOps tooling. The role also supports model validation, QA, performance tuning, production troubleshooting, governance, security, privacy, documentation, and responsible data use. The position is hybrid or remote depending on location, with listed locations in Van Wert or Dublin, Ohio; Waltham, Massachusetts; Alpharetta, Georgia; and Irving, Texas.

Requirements

Master’s degree in Computer Science, Data Science, or a related field; or a bachelor’s degree in one of these fields and 2 years of related experience deploying, maintaining, and supporting machine learning models in production; or 4 years of related production machine learning model experience.

Nice To Haves

Experience developing CI/CD pipelines, automated testing, model packaging, release management, and rollback processes for machine learning or software applications.
Experience with containerization, orchestration, or infrastructure automation tools such as Docker, Kubernetes, Terraform, or similar technologies.
Experience with model monitoring, observability, logging, alerting, performance tracking, data drift detection, or production health monitoring.
Programming experience in Python or similar languages used for machine learning engineering, automation, API development, or data pipeline development.
Experience with SQL, data validation, data quality checks, and data pipeline support for model scoring, retraining, monitoring, or reporting workflows.
Experience developing or supporting APIs, microservices, batch scoring processes, or real-time inference services.
Experience with version control, Git-based workflows, code review practices, documentation, and reproducible development standards.

Responsibilities

Design, build, test, deploy, and support reliable, scalable, maintainable machine learning solutions aligned with business objectives.
Partner with data scientists, actuaries, data engineers, software engineers, and business stakeholders to move models from experimentation into production-ready applications, services, and decision-support workflows.
Develop and maintain automated deployment and CI/CD processes for machine learning models and pricing solutions, including packaging, versioning, validation, release management, rollback procedures, automated testing, environment consistency, and repeatable releases.
Develop and support APIs, services, application integration patterns, and batch or real-time scoring workflows for reliable model inference and consumption of model outputs by business systems.
Support pricing data pipeline development and validation for model scoring, monitoring, retraining, and reporting, partnering with data engineering teams on larger data integration needs.
Implement model monitoring, observability, and logging to track performance, data drift, prediction quality, system reliability, latency, data dependencies, integration points, and other measures of production health.
Contribute to model registries, feature stores, experiment tracking, reusable engineering patterns, templates, tests, documentation, and MLOps tooling to improve traceability, reproducibility, deployment consistency, lifecycle management, and ongoing support.
Apply data governance, security, privacy, and documentation practices to model deployment and monitoring, emphasizing traceability, reproducibility, and responsible data use.
Participate in model validation, QA testing, output review, performance tuning, and production workflow optimization to meet stakeholder, compliance, operational, reliability, maintainability, and cost-effectiveness requirements.
Troubleshoot production issues involving models, data dependencies, model outputs, and integration points in collaboration with software engineers; recommend improvements to reduce operational risk.
Maintain awareness of industry trends, emerging technologies, and modern MLOps practices, and recommend practical improvements to the company’s machine learning engineering capabilities.
Provide technical guidance, peer review, and knowledge sharing on production machine learning practices, deployment standards, monitoring approaches, and operational support.