Data Scientist - Fraud Detection
Entry-level data scientist developing machine learning models and analytical methods to detect fraud, assess risk, and uncover patterns in large transactional datasets. Requires a master’s degree, strong Python and SQL skills, and knowledge of supervised and unsupervised learning.
About the job
Responsibilities
- Develop and deploy machine learning models for fraud detection and risk assessment.
- Perform exploratory data analysis to identify trends, anomalies, and patterns in transactional data.
- Clean, preprocess, and analyze large datasets using Python and data science libraries.
- Collaborate with engineering and business teams to integrate machine learning models into production systems.
- Monitor model performance and refine algorithms to improve accuracy.
- Stay current with advances in fraud detection techniques and machine learning technologies.
Requirements
- Master’s degree in Computer Science, Data Science, Statistics, or a related quantitative field.
- Strong Python programming skills and familiarity with NumPy, Pandas, and scikit-learn.
- Solid understanding of supervised and unsupervised learning, anomaly detection, and classification.
- Experience with SQL and data manipulation or analysis across large datasets.
- Strong problem-solving skills and persistence with deep-dive data exploration.
- Excellent communication skills and ability to work collaboratively.
Nice-to-haves
- Ph.D. in a relevant field.
- TensorFlow or PyTorch experience.
- Prior internship or project experience in fraud modeling or risk analysis.
- Familiarity with Spark, Hadoop, or Dask.
- Knowledge of graph-based fraud detection techniques.
- Experience with AWS, Google Cloud, or Azure.
Compensation and Benefits
- PTO
- Stock options
- Health benefits
Skills
Python, NumPy, pandas, scikit-learn, TensorFlow, PyTorch, SQL, Machine Learning, Anomaly Detection, Spark, Hadoop, Dask, Graph-Based Fraud Detection, AWS, GCP
Similar jobs
Data Science jobs
Coinbase
San Francisco, CA
Data Science Intern supporting product and engineering teams through statistical analysis, experimentation, analytical modeling, and data-driven recommendations. The role requires quantitative academic study or equivalent project experience, plus familiarity with Python and SQL.
Socure
San Francisco, CAData Scientist II developing graph-based algorithms, entity-resolution models, and large-scale data pipelines for identity and deceased-monitoring products. Requires advanced academic training or equivalent experience, strong Python/Scala and SQL skills, and hands-on Spark and AWS experience.
Solace
Redwood City, CA
Associate Data Scientist role for a 2027 college graduate, contributing to forecasting, matching, experimentation, and machine-learning systems. Requires quantitative academic training, Python and SQL proficiency, strong statistical foundations, and clear communication.
Zoox
Foster City, CA
Develop forecasting and scenario-planning capabilities for autonomous fleet operations, covering staffing, demand, charging, supply, and infrastructure. The role suits a currently enrolled quantitative-discipline student with experience in statistical modeling or machine learning and strong analytical communication skills.
Notion
San Francisco, CA
Analyzes product and business data, develops metrics and dashboards, and communicates actionable recommendations to cross-functional teams and leadership. Candidates should be pursuing a quantitative bachelor's or master's degree, with SQL proficiency and familiarity with Python or R.