Civitas Learning is bringing together the best of new technology, design thinking, and data science in our mission to help one million more students graduate each year. We are building a data platform and cloud-based applications to deliver insights and action analytics to the frontlines of education. We are looking for insanely talented people who want to jump in and roll up their sleeves with us to make it all happen, and do the best work of their careers.

We are looking for dedicated engineers to be part of a talented, mission-driven team that is building powerful tools which greatly increase student success.  As a Senior Machine Learning Engineer, you have a unique opportunity to develop key components of a large scale, multi-tenant data collection, data integration, complex data computation, and high speed data presentation and visualization system. You will demonstrate a relentless pursuit of both quality and value while extending and improving our predictive modeling framework.

Responsibilities

• Work collaboratively with data scientists, product managers, and software engineers to develop and support powerful predictive models and machine learning capabilities that fuel applications affecting millions of students.

• Help to architect and build the framework to ingest and transform data variables, select and validate model features and parameters, and build and maintain thousands of machine learning models for hundreds of partner institutions.

• Collaborate with cross-functional team members on ensuring model quality and performance using automated tests and visual analytics.

• Demonstrate and express value of machine learning applications to non-technical stakeholders such as internal Partner Services teams.

Qualifications

• Bachelor’s in Computer Science, Applied Mathematics, Artificial Intelligence, Machine Learning (or equivalent experience). Graduate degree preferred. 

• 4-7 years software development experience with a focus on Java, Python, object-oriented programming, and functional programming.

• Minimum 2 years experience implementing machine learning models that solve real-world problems in a production software environment.

• Deep understanding of statistical concepts including p-values, confidence intervals, bootstrap sampling, and hypothesis testing.

• Familiarity with predictive modeling techniques, machine learning concepts,  and implementation choices according to use cases.

• Knowledge of RDBMS (PostgreSQL, SQL Server, Oracle, DB2, etc.), being proficient with SQL.

Nice to have

• Familiarity with distributed data framework, and experience with open-source ML packages & environments such as Spark ML, Scikit-learn, R, notebooks, etc.

• Experience in Agile development practices (e.g. Scrum, etc.).