Data Scientist (Modeling)

About the Role We are looking for a Data Scientist with strong modeling capabilities who can turn complex business problems into production-ready machine learning solutions. You will own the full lifecycle from problem scoping and model development to deployment and monitoring, with a strong focus on ensuring models deliver measurable business impact. Key Responsibilities Design, build, and deploy predictive models across time-series forecasting, anomaly detection, causal inference, and Monte Carlo simulation. Translate complex model outputs into clear business insights and actionable recommendations for non-technical stakeholders. Productionize models end-to-end, including REST API development, Docker containerization, and deployment on AWS, GCP, or Azure. Build and maintain MLOps capabilities, including model registry, version management, A/B testing, automated retraining, and model performance monitoring. Develop reusable feature engineering pipelines and contribute to Feature Store architecture and governance. Process and analyze large-scale datasets using Spark or equivalent distributed computing frameworks. Monitor data drift, model degradation, and performance decay to ensure long-term model reliability. Build necessary tools and infrastructure independently when existing systems are insufficient. What We’re Looking For Strong hands-on experience in machine learning and statistical modeling, particularly in time-series forecasting, anomaly detection, causal inference, or simulation. Proficiency in Python and common modeling frameworks, with practical experience using techniques such as LSTM, Transformers, XGBoost, Isolation Forest, Autoencoders, or Prophet. Solid engineering experience in model deployment, REST APIs, Docker, cloud platforms, and MLOps practices. Experience with large-scale data processing and distributed computing tools such as Spark. Strong business acumen and ownership mindset, with the ability to translate ambiguous business problems into practical data science solutions and adapt quickly to changing requirements. Nice to Have: Experience in fintech, e-commerce, logistics, or risk-related domains; exposure to LLM applications for structured or tabular data; or experience with real-time inference and streaming technologies such as Kafka or Flink. What We Offer A collaborative and inclusive work environment. Opportunities for professional growth and development. The chance to play a pivotal role in shaping the future of our organization.