Job Description

Company Description

When you’re one of us, you get to run with the best. For decades, we’ve been helping marketers from the world’s top brands personalize experiences for millions of people with our cutting-edge technology, solutions and services. Epsilon’s best-in-class identity gives brands a clear, privacy-safe view of their customers, which they can use across our suite of digital media, messaging and loyalty solutions. We process 400+ billion consumer actions each day and hold many patents of proprietary technology, including real-time modeling languages and consumer privacy advancements. Thanks to the work of every employee, Epsilon India is now Great Place to Work-Certified™. Epsilon has also been consistently recognized as industry-leading by Forrester, Adweek and the MRC. Positioned at the core of Publicis Groupe, Epsilon is a global company with more than 8,000 employees around the world. For more information, visit epsilon.com/apac or our LinkedIn page.

Job Description

Roles & Responsibilities:

Contribute and build an internal product library that is focused on solving business problems related to prediction & recommendation.
Research unfamiliar methodologies, techniques to fine tune existing models in the product suite and, recommend better solutions and/or technologies.
Improve features of the AIQ product to include newer machine learning algorithms in the likes of product recommendation, real time predictions, fraud detection, offer personalization etc
Collaborate with client teams to on-board data, build models and score predictions.
Participate in building automations 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.
Run test cases to tune existing models for performance, check criteria and define thresholds for success by scaling the input data to multifold.
Demonstrate a basic understanding of different machine learning concepts such as Regression, Matrix Factorization, K-fold Validations and different algorithms such as Decision Trees, Random Forrest, K-means clustering.

Qualifications

Minimum Qualifications:

Bachelor’s degree in a quantitative discipline (e.g., Statistics, Economics, Mathematics, Marketing Analytics) or significant relevant coursework
Proficiency with a deep learning framework such as TensorFlow or Keras; minimum 1 years of experience
Exposure to CNN, RNN neural networks based professional projects solving problem in the likes of time series data and image data.
In-depth understanding of LSTM concepts and be able to implement advances techniques such as stacked, bidirectional and seq2seq
Demonstrated proficiency in PYTHON and BIG DATA technologies and the proven ability to program in big data/cloud technologies such as AWS & SPARK; minimum 2 years of experience
A Deep understanding of Recommender Systems and applications around real-time predictions
Experienced with machine learning algorithms such as logistic regression, random forest, XG boost, KNN, SVM, neural network, linear regression, lasso regression and k-means.

Desirable Qualifications

Advanced degree (Master’s/PhD) in Statistics, Economics or other quantitative discipline
Knowledge and understanding of AWS Sagemaker
Working experience in CI/CD tools such as GIT & BitBucket

Additional Information

Epsilon is committed to promoting diversity, inclusion, and equal employment opportunities by using reasonable efforts to attract, recruit, engage and retain qualified individuals of all ethnicities and backgrounds, including, but not limited to, women, people of color, LGBTQ individuals, people with disabilities and any other underrepresented groups, traits or characteristics.