PayPal is seeking a Machine Learning Engineer to build advanced fraud prediction models to enhance fraud prevention across various aspects of their services, including identity, onboarding, authentication, abuse, and product-specific areas.
Requirements
- Familiarity with ML frameworks like TensorFlow or scikit-learn.
- Strong understanding of anomaly detection, supervised learning techniques, and experiential learning methods.
- Familiarity with decision models for identity and authentication.
- Experience driving data instrumentation for experimentation and large-scale data collection.
- Familiarity with building systems that incorporate real-time feedback and continuous learning.
- Knowledge of reinforcement learning, contextual bandits, sequence models, optimization, or graph mining.
- Experience in fraud prevention and detection.
Responsibilities
- Design and implement core decision models for identity, onboarding, authentication, abuse, scam, product-specific models.
- Develop and refine algorithms for detecting anomalies and identifying potential fraud patterns.
- Apply supervised learning techniques to build predictive models that accurately identify fraudulent activities.
- Utilize continual learning methods to continuously improve model performance and adapt to new fraud tactics.
- Conduct experiments, analyze results, and interpret findings to drive innovation and enhance decision-making processes.
- Ensure data integrity and consistency by working closely with business stakeholders and engineers to address critical data challenges.
- Assist in the development and optimization of machine learning models.
Other
- Minimum of 2 years of relevant work experience and a Bachelor's degree or equivalent experience.
- Strong analytical and problem-solving skills.
- 3+ years of experience within ML Engineering or AI Research roles, with demonstrated expertise in building and deploying real-world predictive models.
- Strong interpersonal, written, and verbal communication skills, with experience collaborating across multiple business functions.
- Work closely with cross-functional teams, including tech, operations, and product teams, to integrate fraud prediction models into various systems and processes.
