Develop and implement a set of techniques or analytics applications to transform raw data into meaningful information using data-oriented programming languages and visualization software. Apply data mining, data modeling, natural language processing, and machine learning to extract and analyze information from large structured and unstructured datasets. Visualize, interpret, and report data findings. May create dynamic data reports. As a Data Scientist, apply advanced technical skills in machine learning, statistics, and applied mathematics to business problems to gather requirements from stakeholders and build prototype solutions that demonstrate improvements in key business metrics. Provide expert quantitative guidance on establishing performance metrics for the business and for your model. Become an expert on the data available to solve your problem and build your model, including the ability to integrate querying and collecting this data into your codebase. Work with engineering partners to design and build production-ready solutions based on your prototypes and deploy them. Take ownership of your model performance post-launch and collaborate closely with stakeholders to make sure models meet specifications. Become an expert on the algorithms your model uses to solve your problem, how to tune their parameters, and write code to extend them as necessary. Build robust solutions that will scale to production using cross-validation and offline simulations (“what-if” and sensitivity analysis). Work with senior data scientists to establish modeling goals and milestones, and then own execution and communication on progress with internal and external stakeholders. Independently write model code in Python using the standard EverQuote data science tool stack. Review code in GitHub for other data scientists and machine learning engineers and share learnings and best practices. Document your code and modeling work in shared notebooks, Confluence wiki entries, and live presentations to the team (recorded and shared on our wiki). Key tools include: Jupyter notebooks in our cloud JupyterHub execution environment; Shared EverQuote Python libraries and database interfaces; Scikit-learn’s `Pipeline` API and how it relates to our internal model serving platform Catwalk; Packaging production-ready models to Mlflow; Scheduling and managing notebooks with Papermill. Telecommuting and remote work permitted.

Minimum Requirements: Master’s degree in Statistics, Mathematics, Economics, Finance, Computer Science, or related field and 1 year of experience in the job offered or in a data scientist occupation.


Special Requirements:
Must have some demonstrated experience through academic coursework or experience of the following:

1. Build, train, and evaluate supervised and unsupervised machine learning models using Snowflake SQL, R, and Python’s scikit-learn, Keras, and TensorFlow libraries.
2. Package model binaries for deployment on EverQuote’s model-serving platform using MLflow and internal libraries.
3. Design A/B and multivariate experiments using statistical hypothesis testing to evaluate data science solutions.
4. Design, implement, and test rigorous statistical software to perform sensitivity analysis of model output usings R, Python, and Julia.
5. Design and implement production-ready data science solutions following EverQuote API specifications and using leveraging machine learning design patterns.
6. Own model performance post-launch and collaborate closely with stakeholders to make sure models meet specifications.
7. Provide expert quantitative guidance on product requirements, including establishing performance metrics for the business and data science solutions.
8. Develop quantitative formulations of business problems in close collaboration with subject matter experts and business leaders.

TO APPLY: Please go to www. jobpostingtoday. com, search for job ID 97903 & submit resume.