Machine Learning Scientist II

Machine Learning Scientist II

This role sits centrally within the organization offering a diverse perspective and a vast array of challenges.

We build end-to-end solutions for optimizing standalone pricing algorithms and contributing substantial value to PLS and our partners.

We embrace test and learn by continuously experimenting, analyzing and improving our algorithms which has helped PLS become the fastest growing business within Expedia Group.

What you’ll do:

• Applying statistics methods like confidence intervals, point estimates and sample size estimates to make sound and confident inferences on data and A/B tests

• Building pricing algorithms and configuring the in-house machine learning systems

• Communicating complex analytical topics in a clean & simple way to multiple partners and senior leadership (both internal & external)

• Conducting feature engineering and modifying existing models/techniques to suit business needs

• Modeling rich and complex online travel data to understand, predict and optimize business metrics to help improve the partner experience

• Framing business problems as data science problems with a concrete set of tasks

• Collaborate with technology and business divisions as appropriate

• Articulate solutions, methodologies and frameworks concisely to both technical and non-technical partners

Who you are:

• Bachelors or Master's degree in a technical, or analytical-related, subject such as Computer Science (with focus in areas like Artificial Intelligence, Machine Learning, Natural Language Processing, Data Mining, Data Science), Mathematics, Physics, Statistics, Operations Research, Electrical and Computer Engineering or equivalent experience.

• Must have a base knowledge of ML techniques like Regression, Naïve Bayes, Gradient Boosting, Random Forests, SVMs, Neural Networks, and NLP

• Must have some experience with a programming, statistical, and/or querying languages like Python, R, SQL/Hive, Java

• Helpful to understand distributed file systems, scalable datastores, distributed computing and related technologies (Spark, Hadoop, etc.); implementation experience of MapReduce techniques, in-memory data processing, etc.

• Helpful to be familiar with TensorFlow, and cloud computing (AWS specifically, in a distributed computing context)

• Helpful to be able to effectively communicate and engage with a variety of partners (e.g., internal, external, technical, non-technical people)