Pipl is an identity solutions company. Our products allow organizations to provide frictionless customer experiences and approve trustworthy transactions with greater confidence and speed. We use multivariate linking to establish deep connections among more than 330 billion trust signals—email, mobile phone and social media data that spans the globe—and then look at the big picture to derive identity trust.

About The Role

As a Data Scientist, you will utilize machine learning, programming and domain knowledge to mark trustworthy transactions in an ever-changing domain. Your job will involve quantitative and qualitative analysis of real fraud. You will work closely with other teams, including Product, MLOps and Analytics, to review business problems and identify data requirements necessary to develop predictive models that can help solve them.

About The Candidate

The ideal candidate has a strong background in statistics, machine learning, research design, data analysis, writing production-level code, as well as excellent communication and organizational skills. English proficiency is a must. This position is for a “hands-on” type of person who enjoys tackling real-world data challenges with a can-do attitude and passion for data.

Responsibilities:

• Design and implement ML pipelines using structured and unstructured data for prediction and classification.
• Develop predictive ML models to assess risk, and support operational decision-making.
• Produce explainable model outputs, including key drivers and reason codes appropriate for non-technical users.
• Help define and track success metrics aligned to business value, not just model performance.
• Actively troubleshoot and refine customer models in production.
  
  

Requirements:

• Data Science professional with 1-2 years of experience.
• Master’s degree in Statistics, Computer Science, Mathematics, or a related field.
• Candidates must have a demonstrated research experience.
• Strong proficiency in Python, SQL, and modern ML frameworks
• Proven record of applying machine learning algo to solve real world problems, including regression, classification, unsupervised learning.
• Skilled in handling, cleaning, analyzing, and presenting data.
  
  

Preferred

• Experience with working on identity data or in the fraud prevention industry
• Familiarity with cloud technologies (AWS/GCP/Azure).