On the Data team, we’re developing unsupervised machine learning models and infrastructure to secure a decentralized network from attacks of all kinds. You’ll be working with data primarily in the form of trust scores assigned in a peer-to-peer network, along with other features like geographic information, IP data, observed experience reports (network / machine communication failures,) and more metadata associated with peer-to-peer nodes. Our team is working on one of the world's most sophisticated distributed consensus engines that demands high precision and foresight to prevent unknown attacks. The models we build defend against real-world attacks where money is at stake. The work we do is essential and preventative in nature, as a single prediction error can have drastic impacts. You’ll also have the opportunity to work on research related to economics & financial markets.As part of our team, you will participate in the research on cutting-edge trust / reputation modeling ML techniques and design efforts for the most efficient and practical application of those research techniques to multiple sophisticated problems. You will develop attack scenarios and tests, implement new and existing research, and benchmark performances for a variety of algorithmic variations. You’ll work closely with the protocol team in deploying and testing your models on our scalable infrastructure. If the idea of developing the latest generation of modeling techniques from literature and pushing the boundaries of existing models forward excites you, keep reading.
This is a fully remote role with a preference for candidates working in North American timezones.