Responsibilities :

- Act as a thought partner in defining data science strategy and translating it into practical execution roadmaps.

- Drive experimentation, validation and optimization cycles that balance innovation with real-world reliability.

- Design robust data representations that capture temporal, interaction, and anomaly-based patterns.

- Implement scalable machine learning pipelines for real-time analysis and scoring of user sessions.

- Collaborate with engineering teams to integrate models into production environments.

- Conduct research and stay updated on state-of-the-art approaches in fraud detection, anomaly detection, and behavioral biometrics.

Must-Have :

- Strong background in Machine Learning, Deep Learning, and Statistical Modeling.

- Proficiency in Python and ML libraries (TensorFlow, PyTorch, Scikit-learn, XGBoost).

- Hands-on experience with time-series data, anomaly detection, or fraud detection.

- Strong feature engineering skills, especially with high-dimensional and noisy behavioral data.

- Knowledge of data processing frameworks (Spark, Kafka, Flink, etc.) for streaming/real-time data.

- Experience deploying models into production systems (ML Ops, APIs, containerized environments).

Nice-to-Have :

- Familiarity with behavioral biometrics, keystroke dynamics, or session replay analysis.

- Knowledge of bot detection systems, fraud prevention or cybersecurity applications.

- Experience with big data platforms (Snowflake, Databricks, Hadoop).

- Research background in graph-based ML, similarity search, or embedding techniques.