Data Science Intern

About the role

WHAT MAKES US EPIC?

At the core of Epic’s success are talented, passionate people. Epic prides itself on creating a collaborative, welcoming, and creative environment. Whether it’s building award-winning games or crafting engine technology that enables others to make visually stunning interactive experiences, we’re always innovating.

Being Epic means being a part of a team that continually strives to do right by our community and users. We’re constantly innovating to raise the bar of engine and game development.

ECOSEC

What We Do

Our ECOSEC team provides a safer experience for Epic's users. We work across multiple products and services to improve technology and craft transparent policies so our players and users can have positive experiences on our platforms.

DATA SCIENCE INTERN

What You'll Do

We are looking for a Data Science Intern to join the Ecosystem Security team supporting initiatives related to fraud and abuse detection. As part of the EcoSec team, you will be given a detection problem to own as part of our development cycle. You will work with your data science mentor and the operations analysts who investigate these cases to explore the data, build a model, and measure its impact on how we protect players.

In this role, you will

- Explore large transaction, account, gameplay, and behavioral datasets to characterize how a specific form of abuse actually works

- Build and evaluate statistical or machine learning models that detect abusive activity at scale

- Partner with operations analysts to translate their investigation heuristics into model features, and measure your results against real outcomes like confirmed cases and false positive rates

- Build dashboards or monitoring so the team can track your signal without an analyst in the loop

- Document your data sources, methodology, and findings so the work can be extended after your internship, and present your results to the team

What we're looking for

- Experience with Python for data analysis, pandas and scikit-learn preferred

- Ability to write SQL against large datasets to pull and shape your own data

- A grounding in statistics and machine learning fundamentals, including classification and evaluation metrics beyond accuracy

- A desire to develop strong data science and software development skills

- Genuine curiosity about adversarial problems, specifically how and why people find ways to game a system

- Good interpersonal and communication skills, with demonstrated ability to communicate technical findings within a team

- The ability to react and respond effectively to constructive feedback

- A flexible approach to rapidly evolving problems, and comfort working with messy or sparsely labeled data

- Nice to have: exposure to any of anomaly detection, graph or network analysis, text classification and NLP, or sequence and time-series modeling