Data Scientist

We are looking for a highly talented and motivated Data Scientist. The data science team is responsible for audience solutions, traffic shaping, forecasting, optimal pricing for buyers and sellers (price floors, discounts), latency and processing efficiency optimizations, and other projects. We are looking for someone versatile, methodical, excited by modern technology, and who enjoys focusing on tackling software challenges.

In this role, you will:

• Research and experiment with different machine learning algorithms and techniques for pattern analysis, statistical modeling, feature engineering, and predictive model building.
• Prototype and produce the developed machine-learning solutions.
• Work with Engineers to make sure the models scale well on high volumes of data.
• Use Scala, Java, or Python to utilize Hadoop/Spark to process large-scale datasets.
• Identify, analyze, and interpret trends or patterns in complex log-based data sets.
• Explore and interpret data, analyze results using statistical techniques.
• Use big data skills to bring high volumes of data and data modeling together.
• Regularly demonstrate awareness of priorities of client-driven and internal projects.
• Partner with Data Engineers to get projects into production.
• Conduct and participate in design and code reviews for data science projects.

We are looking for someone with:

• A PhD degree in a quantitative field (e.g., mathematics, statistics, computer science, or engineering).
• In-depth knowledge and experience with Regression, Random Forests, Support Vector Machines, Bagging, Boosting, Decision Trees, Clustering, Optimization, Stochastic Processes.
• Solid understanding of predictive analytics, statistical modeling, and data mining (theory, algorithms, and application).
• Able to make intelligent approximations and design effective, practical, and scalable mathematical models.
• The ability to identify assumptions and the limitations of models/algorithms and the impact on reporting and decision-making.
• Proficiency in Python and SQL (required).
• Experience with Jupyter Notebooks.
• Experience with Spark and "Big data" is desirable.
• Experience with Version Control such as git.
• Comfort working in a Linux/Mac development environment.
• Experience in a software technology company (a plus).
• Knowledge of large language models (a plus).