zorba ai
Website:
zorbaconsulting.in
Job details:
Data Scientist- Job Description
Key Responsibilities
Financial Crime Analytics & Modelling
- Develop machine learning models and analytical solutions to identify suspicious patterns across AML, Fraud, Sanctions, KYC, Transaction Monitoring, and Behavioural Analytics domains.
- Apply supervised and unsupervised ML techniques (clustering, anomaly detection, graph analytics) to uncover hidden networks and unusual behaviour.
- Build and evaluate risk-scoring models, entity resolution tools, and customer behaviour segmentation frameworks.
- Conduct exploratory analysis to identify typologies, red flags, and indicators of financial crime.
Data Engineering, Quality & Governance
- Work with data engineering teams to build reliable data pipelines from internal and external financial crime datasets (transactions, customer profiles, network data, alerts, investigations).
- Ensure models, features, and datasets adhere to governance, model risk management (MRM), audit, and regulatory standards.
- Maintain rigorous documentation covering methodology, assumptions, validation, and performance monitoring.
Business Engagement & SME Collaboration
- Partner with Financial Crime SMEs (AML Investigators, Fraud Analysts, Sanctions Screening teams) to translate typologies and regulatory requirements into data-driven models.
- Provide clear, actionable insights to Compliance, Operations, and Technology stakeholders.
- Support the industrialisation of analytics into production systems and operational workflows.
Model Deployment & Monitoring
- Deploy ML models into production environments using enterprise tools (Azure ML, Databricks, MLflow).
- Implement performance monitoring, drift detection, and periodic model retraining.
- Collaborate with engineers to ensure scalability, resilience, and integration with monitoring platforms and case management workflows.
Required Skills & Qualifications
- Degree in Data Science, Computer Science, Statistics, Mathematics, Engineering, or a related field.
- Strong experience working with financial crime datasets or regulated financial services environments.
- Proficiency in Python (Pandas, NumPy, Scikit-Learn, PySpark) and SQL.
- Understanding of AML, Fraud, Sanctions, KYC, or Transaction Monitoring frameworks.
- Familiarity with techniques relevant to financial crime detection: anomaly detection, clustering, graph/network analytics, NLP (for KYC docs, SAR narratives, etc.).
- Experience with Azure, Databricks, or similar cloud environments.
- Excellent communication skills, with the ability to simplify complex analytics for non-technical stakeholders.
Preferred Qualifications
- Experience in a bank or fintech Financial Crime / Compliance function.
- Knowledge of regulatory requirements (FCA, PRA, MAS, FinCEN, FATF guidance).
- Experience with machine learning model governance, explainability (XAI), and responsible AI practices.
- Experience working with case management systems and screening tools (e.g., Actimize, Fenergo, NICE, Quantexa).
- Exposure to graph databases (Neo4j, TigerGraph) or network analytics.
- Experience implementing end-to-end MLOps workflows.
ender-neutral, inclusive language.]
Example: Determine and develop user requirements for systems in production, to ensure maximum usability
Preferred Qualifications
- Experience in a bank or fintech Financial Crime / Compliance function.
- Knowledge of regulatory requirements (FCA, PRA, MAS, FinCEN, FATF guidance).
- Experience with machine learning model governance, explainability (XAI), and responsible AI practices.
- Experience working with case management systems and screening tools (e.g., Actimize, Fenergo, NICE, Quantexa).
- Exposure to graph databases (Neo4j, TigerGraph) or network analytics.
- Experience implementing end-to-end MLOps workflows.
- Data scientist- Job description
Key Responsibilities
Financial Crime Analytics & Modelling
- Develop machine learning models and analytical solutions to identify suspicious patterns across AML, Fraud, Sanctions, KYC, Transaction Monitoring, and Behavioural Analytics domains.
- Apply supervised and unsupervised ML techniques (clustering, anomaly detection, graph analytics) to uncover hidden networks and unusual behaviour.
- Build and evaluate risk-scoring models, entity resolution tools, and customer behaviour segmentation frameworks.
- Conduct exploratory analysis to identify typologies, red flags, and indicators of financial crime.
Data Engineering, Quality & Governance
- Work with data engineering teams to build reliable data pipelines from internal and external financial crime datasets (transactions, customer profiles, network data, alerts, investigations).
- Ensure models, features, and datasets adhere to governance, model risk management (MRM), audit, and regulatory standards.
- Maintain rigorous documentation covering methodology, assumptions, validation, and performance monitoring.
Business Engagement & SME Collaboration
- Partner with Financial Crime SMEs (AML Investigators, Fraud Analysts, Sanctions Screening teams) to translate typologies and regulatory requirements into data-driven models.
- Provide clear, actionable insights to Compliance, Operations, and Technology stakeholders.
- Support the industrialisation of analytics into production systems and operational workflows.
Model Deployment & Monitoring
- Deploy ML models into production environments using enterprise tools (Azure ML, Databricks, MLflow).
- Implement performance monitoring, drift detection, and periodic model retraining.
- Collaborate with engineers to ensure scalability, resilience, and integration with monitoring platforms and case management workflows.
Preferred Qualifications
- Experience in a bank or fintech Financial Crime / Compliance function.
- Knowledge of regulatory requirements (FCA, PRA, MAS, FinCEN, FATF guidance).
- Experience with machine learning model governance, explainability (XAI), and responsible AI practices.
- Experience working with case management systems and screening tools (e.g., Actimize, Fenergo, NICE, Quantexa).
- Exposure to graph databases (Neo4j, TigerGraph) or network analytics.
- Experience implementing end-to-end MLOps workflows.
Skills: neuro-linguistic programming (nlp),numpy,python,genai,pandas,ml
Click on Apply to know more.