- The ideal candidate will have a strong background in building machine learning and deep learning models particularly in fraud detection, transaction monitoring, or risk analytics and will be responsible for the end-to-end model lifecycle, from data exploration to production deployment and monitoring.

Key Responsibilities :

- Design and develop ML/DL models for fraud detection, risk scoring, and transaction monitoring.

- Experiment with supervised, unsupervised, and semi-supervised learning techniques for anomaly detection.

- Manage data pre-processing, feature engineering, training, validation, deployment, and continuous improvement.

- Implement scalable and reproducible ML pipelines.

- Deploy and maintain models in production using MLOps frameworks such as MLflow, Kubeflow, Airflow, or AWS Sagemaker.

- Implement CI/CD for model updates and retraining.

- Partner with data engineering teams to build robust data pipelines, feature stores, and real-time scoring infrastructure.

- Build systems for automated model evaluation, drift detection, and performance reporting.

- Work closely with product, compliance, and risk teams to define fraud detection strategies and translate business needs into ML solutions.

Required Skills & Qualifications:

- Mandatory 5 years of experience as Data Scientist / ML Engineer

- Bachelors or Masters degree in Computer Science, Data Science, Statistics, Applied Mathematics, or a related field.

- Proficiency in Python (NumPy, Pandas, Scikit-learn, TensorFlow/PyTorch).

- Experience with fraud detection, transaction monitoring, or anomaly detection.

- Strong background in machine learning and deep learning architectures (RNN, LSTM, Transformer, GNN, GCN).

- Experience with MLOps tools MLflow, Kubeflow, Airflow, or AWS Sagemaker.

- Familiarity with data pipelines and distributed systems (Spark, Kafka, etc.).

- Experience deploying ML models on AWS / GCP / Azure environments.

Soft Skills :

- Strong communication skills to collaborate with technical and business teams.

- Ability to work independently and drive results in a fast-paced environment.

Preferred Experience :

- Hands-on experience with real-time fraud detection or behavioral anomaly detection.

- Exposure to financial transactions, payment gateways, or card network ecosystems.

- Understanding of explainable AI (XAI) tools such as SHAP, LIME, or Captum.

- Familiarity with graph-based fraud detection approaches.

What We Offer :

- Opportunity to build next-generation fraud detection systems at scale.

- Collaborative and high-growth work environment.

- Competitive compensation and benefits.

- Chance to work on real-world AI/ML challenges in the fintech domain from our Mumbai on-site office.