About the role
We are looking for a Data Science Manager with a strong background in managing data-driven solutions to lead a high-performing DS team within the banking sector. This role combines ML expertise, team leadership, and cross-functional communication, with a focus on scorecard development, model performance, and portfolio risk monitoring.
Responsibilities
- Advanced ML-modeling and data-exploration: ensembles and AI-algorithms, AI-initiatives management, external AI-services integration. Focus on models and solutions for: credit, fraud, marketing, collection and contact strategies, text, speech and behavioral analytics, dynamic pricing and limits. - Stakeholders' expectations management: communication with risk (portfolio) team, collection team, other business units on score-modelling and backlog prioritization, task clarification. - DS-team management: recruitment, training, performance improvement, scrum-servicing, task-management. Improvement DS-team communication with consumers and business needs understanding. - Environment, process and tools management: git, Jira board, Confluence content, Agile rituals. - ML-data management: colabration with DWH-team; data-availability, reliability and quality assessment; new/existent data-sources integrations support and management, data-flow stability control, feature-store administation. - ML-model lifecycle management: from business needs identification to "sell", deployment and production-test stage. ML-models stability monitoring and quality control, reassessment and proactive quality improvement (re-calibration/ re-building). - Knowledge management: Maintain up-to-date project documentation, implement standards, control discipline and maintain actuality for confluence descriptions, feature-store meta-data, git documentation, internal experience sharing and handover, new methodologies and tools review and implementation.
Requirements
- Demonstrated experience working in fintech or banking, especially within emerging markets. - Hands-on experience developing ML scoring models for text, speech, behavioral analytics, and dynamic modeling in card businesses. - Strong programming skills in Python and SQL for data analysis, modeling, and automation. - Proven experience with machine learning techniques, including:
- Regression, classification, ranking, boosting - Graph-based models, neural networks, NLP, and large language models (LLMs)
- Solid understanding and practical implementation of AI concepts and systems. - Familiarity with MLOps, including data pipelines, model deployment, and productionizing machine learning solutions. - Experience with cloud computing platforms, especially AWS (highly preferred). - Proficiency with BI and data visualization tools such as PowerBI, Excel, Tableau, or Grafana. - Prior exposure to risk management or analytics, particularly within the cards or payments space. - Strong grasp of Agile and Scrum methodologies in a data or engineering environment. - Excellent communication and presentation skills, with the ability to simplify complex data concepts for both technical and non-technical audiences. - Fluent in spoken English.
Text as published by Renmoney. We don't edit postings; apply and ask questions on the employer's site.