Machine Learning Engineer, Fraud (Crypto & Debit Card)
0 viewsXoomChennaiOnsite
1-6 years
Posted today
- AWS
- Azure
- GCP
- Git
- Python
- Spark
Job Summary
This job will support the development and implementation of machine learning models that detect and prevent fraud across our Crypto and Debit Card portfolios. You will work alongside senior ML engineers, data scientists, software engineers, and fraud strategy teams to build and improve AI/ML solutions that protect customers and reduce losses. Your role will involve preparing data, building features, training and evaluating models, and helping deploy and monitor them in production. This is a great opportunity to grow your ML engineering skills on real-time systems that make high-impact decisions.
Key Responsibilities
- Assist in developing and improving ML models to detect fraud across debit card transactions and crypto buy/sell/transfer activity.
- Preprocess, clean, and analyze large transactional, behavioral, and device datasets to support model development.
- Build and test features under the guidance of senior engineers, such as transaction velocity and behavioral signals.
- Train, evaluate, and compare models using appropriate fraud metrics (precision, recall, false positive rates).
- Support the deployment and maintenance of ML models in production, including pipeline updates and testing.
- Help monitor deployed models for performance and drift, and flag issues to the team.
- Collaborate with data scientists, engineers, and fraud operations partners to understand fraud patterns and business needs.
- Write clean, well-tested code and contribute to model documentation.
Qualifications
- 1+ years of relevant experience (internships, co-ops, or academic projects count) and a Bachelor's degree OR any equivalent combination of education and experience.
- Familiarity with ML frameworks like TensorFlow, PyTorch, or scikit-learn.
- Proficiency in Python and SQL.
- Foundational understanding of machine learning concepts, statistics, and model evaluation.
Preferred Qualifications
- Internship or project experience in fraud detection, risk, anomaly detection, or payments.
- Exposure to cloud platforms (AWS, Azure, GCP) and big data tools such as Spark.
- Familiarity with gradient-boosted models (XGBoost, LightGBM) and transformer architecture.
- Experience with version control (Git) and software engineering fundamentals.
- Master's degree in Computer Science, Machine Learning, Statistics, or a related field.