Entry-Level Data Scientist

14 Minutes ago • 5 Years +

Data Analysis

Job Description

We are looking for a motivated Entry-Level Data Scientist to join our Fraud Detection team. In this role, you will leverage your machine learning and data analysis skills to identify fraudulent activities, build predictive models, and uncover hidden patterns in large datasets. You will work closely with cross-functional teams to develop scalable solutions that enhance our fraud detection capabilities. This is a great opportunity to grow your skills in a fast-paced, data-driven environment while making a real impact in the fight against fraud. Key responsibilities include end-to-end model development, advanced feature engineering, algorithm innovation, and large-scale data processing.

Good To Have:

Experience with PySpark is a significant plus.

Must Have:

Lead the full lifecycle of fraud detection features and models.
Develop highly predictive features from complex, large-scale, multi-dimensional data.
Research, design, and implement state-of-the-art machine learning algorithms.
Work with massive, noisy, and imbalanced datasets using tools like Spark, SQL.
Partner closely with Engineering for robust, low-latency model deployment.
Conduct deep-dive analyses on fraud attacks and extract actionable insights.
Master's or PhD in Computer Science, Statistics, Mathematics, or a related quantitative field.
5+ years of professional experience in data science, with a focus on fraud detection, cybersecurity, or adversarial domains.
Deep, hands-on experience with machine learning lifecycle in a production environment.
Strong programming skills in Python and proficiency with SQL.
Solid understanding of both classic and modern machine learning models.
Proven experience with feature engineering.
Experience with large-scale data tools (Spark, Hadoop) and cloud platforms (AWS, GCP, Azure).
Professional proficiency in written and spoken English.
Excellent communication skills.
Based in Japan.

Perks:

Add these skills to join the top 1% applicants for this job

saas-business-models

cross-functional

communication

data-analytics

data-structures

game-texts

cross-functional-collaboration

prototyping

aws

azure

hadoop

spark

model-deployment

data-science

deep-learning

neural-networks

python

algorithms

sql

machine-learning

About DataVisor:

DataVisor is the world’s leading AI-powered Fraud and Risk Platform that delivers the best overall detection coverage in the industry. With an open SaaS platform that supports easy consolidation and enrichment of any data, DataVisor's fraud and anti-money laundering (AML) solutions scale infinitely and enable organizations to act on fast-evolving fraud and money laundering activities in real time. Its patented unsupervised machine learning technology, advanced device intelligence, powerful decision engine, and investigation tools work together to provide significant performance lift from day one. DataVisor's platform is architected to support multiple use cases across different business units flexibly, dramatically lowering total cost of ownership, compared to legacy point solutions. DataVisor is recognized as an industry leader and has been adopted by many Fortune 500 companies across the globe.

Our award-winning software platform is powered by a team of world-class experts in big data, machine learning, security, and scalable infrastructure. Our culture is open, positive, collaborative, and results-driven. Come join us!

Position Overview:

Key Responsibilities:

End-to-End Model Development: Lead the full lifecycle of fraud detection features and models, from ideation and data exploration to prototyping, productionizing, and monitoring.
Advanced Feature Engineering: Develop highly predictive features from complex, large-scale, multi-dimensional data, including user behavior, device intelligence, network graphs, and transaction records.
Algorithm Innovation: Research, design, and implement state-of-the-art machine learning algorithms, combining supervised, unsupervised, and semi-supervised techniques to detect novel and evolving fraud patterns.
Large-Scale Data Processing: Work with massive, noisy, and imbalanced datasets (billions of events) using tools like Spark, SQL, and our proprietary AI platform.
Cross-Functional Collaboration: Partner closely with Engineering to ensure robust, low-latency model deployment and with Product Management to translate complex client needs into technical solutions.
Fraud Strategy & Analysis: Conduct deep-dive analyses on fraud attacks, extract actionable insights, and translate them into improved detection strategies and rules.
Mentorship: Provide technical guidance and mentorship to junior data scientists, fostering a culture of excellence and continuous learning.

Requirements

Master's or PhD in Computer Science, Statistics, Mathematics, or a related quantitative field.
5+ years of professional experience in data science, with a significant focus on fraud detection, cybersecurity, or a related adversarial domain.
Deep, hands-on experience with machine learning lifecycle in a production environment.
Strong programming skills in Python (must-have) and proficiency with SQL. Experience with PySpark is a significant plus.
Solid understanding of both classic machine learning models (Logistic Regression, Gradient Boosting, etc.) and modern techniques (Deep Learning, Graph Neural Networks).
Proven experience with feature engineering and a keen intuition for what makes a feature predictive and robust in a dynamic environment.
Experience with large-scale data tools (Spark, Hadoop, etc.) and cloud platforms (AWS, GCP, Azure).
Professional proficiency in written and spoken English, with the ability to collaborate effectively in a global, cross-functional team.
Excellent communication skills, with the ability to explain complex technical concepts to both technical and non-technical audiences.
Based in Japan