Fingerprint is looking to enhance the accuracy and performance of its Smart Signals product to combat online fraud more effectively by developing algorithms capable of transforming raw, noisy, and unlabeled data into actionable insights about browsers and devices.
Requirements
- Strong foundational knowledge in machine learning algorithms and statistical methods
- Experience with supervised learning techniques such as gradient boosting, logistic regression, and working with categorical data
- Proficiency in Python and SQL for data analysis and model development
- Experience with version control systems like Git and basic software engineering principles
Responsibilities
- Develop and refine algorithms that convert raw, noisy, and unlabeled data into meaningful insights regarding browsers and devices
- Design, implement, and evaluate supervised learning models to enhance detection accuracy
- Collaborate with ML engineers, data scientists, and software engineers to advance technical capabilities and integrate solutions
- Conduct exploratory data analysis to identify anomalies, investigate data patterns, and answer ad-hoc analytical questions
- Run experiments to address ML engineering challenges, including real-time inference, model training automation, and system optimization
- Participate in the full model lifecycle, from data preprocessing and feature engineering to deployment and monitoring
Other
- 2–4 years of professional experience in Data Science or Machine Learning
- Excellent communication skills in English, comfortable working within a remote, global team
- Opportunity to work remotely in a flexible, inclusive environment
- Collaborate with a diverse and talented global team
- Engage in innovative projects with a focus on open-source development
