Data Scientist
Sardine- Full Time
- Senior (5 to 8 years)
Candidates should possess a Master’s degree in a quantitative field such as Computer Science, Statistics, Mathematics, or a related discipline, and typically 5+ years of experience in data science, with a focus on machine learning and fraud detection. Strong programming skills in Python are essential, along with experience in developing and deploying ML models in a production environment. Experience with large datasets and distributed computing frameworks is preferred.
As a Staff Data Scientist at Signifyd, you will expand ML capabilities by identifying, prototyping, and integrating new technologies to enhance fraud detection effectiveness and scalability. You will drive experimentation at scale by developing robust frameworks and implementing rapid iteration of fraud detection models. Furthermore, you will architect and optimize ML pipelines to support both offline and online measurement of model performance, and collaborate closely with engineering, product, and risk teams to align ML architecture with business goals. Finally, you will lead and mentor data scientists and engineers, fostering a culture of innovation and excellence in ML practices.
Fraud protection for online retailers
Signifyd specializes in fraud protection for online retailers, helping them detect and prevent fraudulent activities. The company provides a platform that uses machine learning and artificial intelligence to analyze transactions in real-time, identifying potential fraud. This service allows retailers to reduce chargebacks and approve more legitimate orders, ultimately increasing their revenue. Signifyd differentiates itself by offering a financial guarantee on approved transactions, meaning they will cover costs if a transaction they approve is later found to be fraudulent. This added security builds trust with clients. Operating globally, Signifyd ensures transparency with real-time data on system performance, allowing retailers to focus on their core business without the constant worry of fraud.