About the job
Join Our Innovative Team!
HealthCare.com stands at the forefront of the insurtech industry, rapidly transforming the way individuals shop for health insurance. By harnessing cutting-edge technology and sophisticated data science, we have created tailored proprietary products that align with consumer needs, boost customer satisfaction, and eliminate the complexities associated with purchasing insurance.
About the Position
We are on the lookout for a Senior Data Scientist specializing in Production Machine Learning to take charge of our essential production bidding system. This role is not focused solely on research or ticket management; instead, you will collaborate directly with product, engineering, and business teams to identify challenges, devise solutions, and deploy production-ready models that significantly drive our business forward.
We value candidates who are inquisitive, practical, and flexible—data scientists who can seamlessly navigate between modeling, data engineering, and software development as the situation demands. While prior experience is important, your ability to think critically and learn swiftly is paramount.
This role is part of our dedicated data team, which includes data engineers, data scientists, and analysts.
Your Responsibilities
Take ownership of and enhance machine learning models operating in production, including monitoring, troubleshooting, and ongoing improvement.
Train, fine-tune, and optimize models for a real-time or near-real-time bidding and decision-making system.
Collaborate with stakeholders to clarify complex problems, establish success metrics, and convert business needs into effective technical solutions.
Design and implement feature engineering pipelines that balance model performance, latency, and maintainability.
Produce production-quality Python code (beyond just notebooks) and work with engineering teams on deployment, CI/CD, and system architecture.
Evaluate model performance through logs, metrics, and offline analysis to uncover issues and improvement opportunities.
Contribute to the development of data pipelines and infrastructure as necessary (e.g., ETL processes, materialized views, model inputs).
Make informed trade-offs between theoretical optimization and practical, reliable, and expedient solutions.
What We Seek
Essential Qualifications
Extensive experience with Python, particularly in writing code that operates within production systems.
Proficient SQL skills and hands-on experience with analytical databases (Snowflake or equivalent).
Practical experience in training and tuning tree-based models (e.g., LightGBM, XGBoost, CatBoost) using real, complex datasets.
Experience in deploying, maintaining, or managing ML models beyond the experimental phase (APIs, batch jobs, or streaming systems).
Comfortable working across various domains and adapting to different challenges as they arise.