Twitch’s Video backend teams build and support a highly scalable low latency video platform, enabling millions of people to become, and interact with entertainers around the world. This requires highly dedicated individuals to solve unique and challenging problems.
Our team is in charge of the viewcount systems powering Twitch, making sure that popularity metrics displayed on the site are accurate and resilient against fraud. In order to achieve that we develop general fraud detection infrastructure that also benefit other teams.
Twitch today handles incoming video from tens of thousands of simultaneous broadcasters, and supports massive audiences in the tens of millions. You will operate in a fast, dynamic, demanding environment where no two days are ever the same. You will develop statistical models, services, and algorithms operating on large complex data sets to understand the impact of abuse to our community’s ecosystem and prevent it.
As a video fraud analyst for Twitch, you are passionate about cutting-edge technologies and have experience with analyzing large scale data, and are interested in applying your models as part of large scale distributed systems resilient against all kinds of failure conditions and attack patterns. You will be a key contributor to the strategy for shielding our community against abuse at Twitch. You are an independent, critical thinker, a bit of a troublemaker with sound metric judgment. You have a passion for outreach, coaching others, solving technological challenges and setting standards. You can balance short term requirements with the ability to see the big picture and formulating key strategic plans to make sure Twitch continues to act in the interest of its community in preventing fraud.
- Apply advanced statistical methods to large complex data sets to understand abuse in our community ecosystem. Contribute strategy, models, measures, algorithms and implementation against known and unknown vectors of abuse.
- Communicate highly technical results and methods clearly.
- Manage technological solutions for streamlining quality assurance and producing scalable solutions for newly designed and defined workflows.
- Create consensus and maintain communication. Work closely with other engineers and interact cross-functionally with a wide variety of people and teams including.
- Perform fraud and spam investigations using a wide variety of data sources, identify product vulnerabilities and deploy measures to prevent abuse.
- MS/PhD degree or equivalent practical experience
- 3 years of SQL experience (e.g., SQL, MySQL, MapReduce)
- Experience in data analysis and statistical modeling
- Experience with data modeling systems
- Experience designing and writing high quality code. Experience building distributed systems is a plus
- Experience with fraud detection, anomaly detection, classification systems, ranking systems, social graph analysis, or similar
- Experience collecting, managing and synthesizing large data sets and information from disparate sources, statistical modeling, data mining and data analysis
- Consultative problem solving coupled with strengths in data management, metrics analysis, experiment design and automation
- Highly analytical with strong demonstrated track record of problem solving and a quantitative mind, capable of translating analytical insights into actions.
Twitch (an Amazon.com
subsidiary) is the world’s leading video platform and community for gamers, with more than 100 million visitors per month. We connect gamers from around the world by allowing them to broadcast, watch, and chat with each other. Twitch’s live and on-demand video platform forms the backbone of a distribution network for video game broadcasters including pro players, tournaments, leagues, developers and gaming media organizations. Twitch is leading a revolution in gaming culture, turning gameplay into an immersive video experience. Learn more at: http://twitch.tv
We are an equal opportunity employer and value diversity at Twitch. We do not discriminate on the basis of race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.