About this role
Epsilon is the leader in outcome-based marketing. We enable marketing that’s built on proof, not promises. Through Epsilon PeopleCloud, the marketing platform for personalizing consumer journeys with performance transparency, Epsilon helps marketers anticipate, activate, and prove measurable business outcomes. Powered by CORE ID®, the most accurate and stable identity management platform representing 200+ million people, Epsilon’s award-winning data and technology is rooted in privacy by design and underpinned by powerful AI. With more than 50 years of experience in personalization and performance working with the world’s top brands, agencies, and publishers, Epsilon is a trusted partner leading CRM, digital media, loyalty, and email programs. Positioned at the core of Publicis Groupe, Epsilon is a global company with over 8,000 employees in over 40 offices around the world. For more information, visit epsilon.com. Follow us on Twitter at @EpsilonMktg.
Roles & Responsibilities
- Contribute and build an internal product library that is focused on solving business problems related to prediction & recommendation.
- Participate in building automation and standalone applications around machine learning algorithms to enable a “One Click” solution to getting predictions and recommendations.
- Analyze large datasets, perform data wrangling operations, apply statistical treatments to filter and fine-tune input data, engineer new features, and eventually aid the process of building machine learning models.
- Apply object-oriented programing and apply design patterns as required, and, participate in designing new features and enhancements to the ML product.
- Work closely with data scientists and help the team with model refresh process and periodic scoring, fixing bugs, re-deploying models in various environments involved in the product life cycle.
- Expand and maintain a product based in python and hosted in cloud platforms. Maintain versioning of the library and ensure the new features are integrated into the existing product without affecting the current versions.
- Run test cases to tune existing models for performance, check criteria and define thresholds for success by scaling the input data to multifold.
- Collaborate with client teams to onboard data, build models, and score predictions.
Minimum Qualifications
- Bachelor’s degree in an engineering discipline, but preferably computer science or significant relevant coursework
- Experience building applications from the ground up and exposure to object-oriented programing and design patterns will be highly preferred.
- Proficiency with python advanced concepts such as multi-threading and templating
- Highly skilled in SQL and strong data extraction skills
- Hands-on experience working with very large datasets, including statistical analyses, data visualization, data mining, and data cleansing/transformation
- Demonstrated proficiency in PYTHON and BIG DATA technologies and the proven ability to program in big data/cloud technologies such as AWS & SPARK; minimum 1 year of experience
Desirable Qualifications
- Basic understanding of machine learning algorithms (Decision Trees, Random Forrest & Regression, etc.) and statistical concepts (T-TEST, CHISQ Test, Confidence Interval, Standard deviation, p-value, etc.)
- Knowledge and understanding of AWS Sagemaker
- Working experience in CI/CD tools such as GIT & BitBucket