Job Description :

We are looking for an experienced AI/ML Data Scientist to join our team and work on high-impact use cases across payments, fraud detection, risk analytics, and financial services. The ideal candidate should have strong hands-on experience in developing and deploying machine learning models in production environments, preferably within payments, fintech, banking, or other high-volume transactional domains.

Key Responsibilities :

Model Development :

- Design, develop, train, validate, and deploy machine learning models for real-time transaction fraud detection, card-not-present (CNP) risk scoring, authorization decline/approval optimization, chargeback and dispute prediction, merchant risk scoring, and AML/transaction-monitoring anomaly detection.

- Engineer and optimize features using transactional, behavioral, device, and network data while meeting strict latency requirements for real-time scoring.

- Evaluate and select appropriate machine learning techniques based on business requirements, including gradient boosting, deep learning, graph-based fraud detection, anomaly detection, and time-series modeling.

- Work with large and complex datasets to identify patterns, fraud signals, and opportunities for improving risk decisioning.

Productionization and MLOps :

- Collaborate with Engineering teams to deploy ML models into real-time and batch processing pipelines.

- Ensure production models meet requirements for reliability, scalability, latency, monitoring, and rollback safety.

- Develop and maintain monitoring frameworks for model drift, data quality, performance degradation, and fraud-loss KPIs.

- Contribute to MLOps practices including model, feature, and data versioning, reproducible training pipelines, CI/CD, model validation, and retraining processes.

- Implement A/B testing, shadow testing, and controlled model rollout frameworks.

AI and LLM Applications :

- Apply modern AI and LLM technologies such as Claude and GPT to accelerate data science and analytics workflows.

- Explore LLM-based solutions for automated feature exploration, model documentation, anomaly narrative generation, and data pipeline code generation/review.

- Develop applied AI use cases for fraud, risk, and compliance workflows, including summarization of suspicious activity patterns for analyst review and SAR drafting support with appropriate human oversight.

Cross-Functional Collaboration and Governance :

- Collaborate with Fraud, Risk, Compliance, Engineering, Product, and Client Services teams to develop effective and explainable ML solutions.

- Ensure model outputs are explainable, auditable, and defensible for internal stakeholders, auditors, regulators, and card scheme risk teams.

- Present model performance, analytical findings, and business trade-offs to technical and non-technical stakeholders.

- Ensure data processing and model development comply with PCI DSS, data residency requirements, security standards, and internal data governance policies.

Required Qualifications :

- 8+ years of overall professional experience, including at least 3+ years of hands-on experience as a Data Scientist or ML Engineer.

- Experience in payments, fintech, banking, financial services, fraud detection, risk analytics, or other high-volume transactional environments is preferred.

- Strong programming skills in Python and SQL.

- Hands-on experience with Pandas, Scikit-learn, XGBoost, LightGBM, PyTorch, or TensorFlow.

- Strong understanding of classification, anomaly detection, imbalanced datasets, and rare-event modeling.

- Proven experience developing and deploying machine learning models into production environments.

- Experience with model monitoring, performance tracking, drift detection, and model retraining.

- Hands-on experience with cloud-based data and ML platforms such as AWS, GCP, or Azure.

- Experience with platforms/tools such as SageMaker, Vertex AI, or Databricks.

- Knowledge of data engineering technologies such as Spark, Airflow, or similar tools.

- Understanding of financial services data security, PCI DSS, data minimization, access controls, and regulatory requirements.

- Strong communication skills with the ability to explain model performance, precision/recall, false-positive costs, latency, and other ML trade-offs to business stakeholders.

Preferred Qualifications :

- Experience with payments-specific fraud typologies such as CNP fraud, account takeover, first-party fraud, synthetic identity, BIN attacks, and card testing.

- Experience with graph-based or network analysis techniques for fraud ring and merchant collusion detection.

- Familiarity with card scheme rules and risk parameters, including Visa and Mastercard fraud/risk attributes.

- Experience applying LLMs such as Claude or GPT to data science, analytics, feature engineering, automated EDA, reporting, or analyst-facing applications.

- Experience with real-time streaming technologies such as Kafka and Flink.

- Experience working with low-latency ML scoring systems.

- MSc, PhD, or equivalent practical experience in Statistics, Computer Science, Applied Mathematics, Physics, Operations Research, or another quantitative discipline.

Key Skills :

Python, SQL, Machine Learning, Data Science, Fraud Detection, Payments, Risk Analytics, XGBoost, LightGBM, PyTorch, TensorFlow, Scikit-learn, MLOps, AWS, GCP, Azure, Databricks, Spark, Airflow, Kafka, Flink, Graph Analytics, Anomaly Detection, Deep Learning, LLM, GenAI

Candidate Profile :

The ideal candidate will be a hands-on AI/ML professional with strong production experience, excellent problem-solving skills, and exposure to fraud, payments, risk, or financial services. The candidate should be comfortable working with large-scale transactional data, building real-time ML solutions, collaborating with cross-functional teams, and translating complex analytical results into actionable business insights.