Senior Hiring - AIML (BFS)

Tiger Analytics; Chennai; Vor Ort; INR 4.200.000 - 7.500.000; Vollzeit

Zusammenfassung

Tiger Analytics in Chennai, India, seeks a Senior Lead Data Scientist to own end-to-end risk and analytics modelling initiatives. You will drive the data science lifecycle from data sourcing to deployment and governance, leading production-grade solutions across risk, fraud, and customer analytics.

The role requires 12+ years in data science and 5+ years of leadership, with deep hands-on Python, SQL, ML, and actuarial modelling experience across banking/fintech sectors.

Qualifikationen

• 12+ years of total experience in Data Science or related quantitative disciplines, with hands-on coding.
• 5+ years of leadership experience managing Data Science / ML teams delivering production-grade solutions.
• Strong experience in Risk & Predictive Modeling including Time-to-Default and PD models.
• Deep hands-on expertise in Python, SQL, ML methods, and model validation.

Aufgaben

• Lead end-to-end Risk & Analytics Modelling across data sourcing, cleaning, feature engineering, modeling, validation, deployment, and governance.
• Design and oversee Risk & Credit Modelling, Fraud Analytics, Customer Propensity Modelling, and Actuarial analytics.
• Establish and optimize Production-Scale MLOps, model governance, and stakeholder communications.
• Guide strategic analytics roadmap and mentor high-performing data science teams.

Kenntnisse

Python

SQL

Machine Learning

Statistical Modeling

Leadership

Mentorship

Communication

Team Management

Data Science

Ausbildung

Master's or PhD in Computer Science or Data Science

Tools

ML frameworks

Version Control (Git)

Jobbeschreibung

• End-to-End Risk & Analytics Modelling: Lead the full data science lifecycle—from data sourcing, cleaning, feature engineering, and exploratory analysis to developing, validating, and deploying sophisticated predictive models across risk and customer analytics use cases.
• Risk & Credit Modelling: Design and oversee advanced Time-to-Default / Probability of Default models, incorporating behavioural, transactional, financial, and other relevant data to improve risk prediction, portfolio monitoring, and decision-making.
• Fraud Analytics & Detection: Develop and review sophisticated fraud detection models using Machine Learning, statistical techniques, anomaly detection, and behavioural patterns to identify emerging fraud risks and minimize financial losses.
• Customer Propensity Modelling: Build and optimize propensity-to-churn and customer behaviour models to identify at-risk customers, understand behavioural drivers, and enable targeted retention and engagement strategies.
• Actuarial & Statistical Modelling: Apply advanced actuarial models, statistical techniques, and predictive analytics to support pricing, risk assessment, forecasting, portfolio management, and business planning.
• Advanced Algorithmic Design: Evaluate, select, and develop appropriate Machine Learning, Deep Learning, statistical, and predictive modelling approaches, ensuring strong model accuracy, interpretability, stability, and statistical robustness.
• Model Validation & Deep Technical Review: Remain deeply hands-on in reviewing model design, assumptions, feature engineering, methodologies, validation approaches, performance metrics, and code. Challenge technical decisions and ensure models meet rigorous quality and business standards.
• Production-Scale MLOps: Establish and optimize end-to-end MLOps frameworks, covering model development, version control, deployment, monitoring, model performance tracking, drift detection, retraining, and operational governance across cloud environments.
• Model Governance & Operationalization: Define and enforce best practices for model governance, documentation, validation, explainability, performance monitoring, and lifecycle management, ensuring models are production-ready and scalable.
• Strategic Planning & Thought Leadership: Drive the analytics roadmap by identifying high-value opportunities, defining modelling priorities, anticipating emerging analytical needs, and shaping the organization's Data Science and AI strategy.
• Executive Advisory & Stakeholder Management: Represent the Data Science function with senior management and enterprise stakeholders. Communicate complex analytical findings, model outcomes, risks, and recommendations clearly and confidently, translating technical insights into business decisions and strategic actions.
• Team Leadership & Mentorship: Lead, mentor, and develop high-performing teams of data scientists, ML engineers, and analytics professionals. Set technical standards, promote deep analytical thinking, and foster a culture of engineering excellence and continuous learning.

• 12+ years of total experience in Data Science, Machine Learning, Advanced Analytics, Risk Analytics, Fraud Analytics, Actuarial Analytics, or related quantitative disciplines, with significant experience as a hands-on, code-writing practitioner.
• 5+ years of proven leadership experience managing, mentoring, and growing specialized Data Science / ML teams delivering production-grade analytical solutions.
• Strong experience in Risk & Predictive Modeling: Demonstrated expertise in Time-to-Default / Probability of Default, fraud modeling, propensity-to-churn, customer behavior modeling, and/or actuarial models.
• Deep hands-on technical expertise: Strong command of Machine Learning, statistical modeling, predictive analytics, Python, SQL, and relevant ML frameworks. Should be capable of going deep into model methodologies, assumptions, feature engineering, code, validation, and performance rather than operating purely at a managerial level.
• Education: Master's or PhD in Computer Science, Data Science, Statistics, Mathematics, Engineering, Actuarial Science, Economics, or another highly quantitative discipline (preferred).
• Domain Track Record: Prior experience delivering production-grade analytics and predictive modeling solutions within Banking, Financial Services, Insurance, FinTech, or other highly analytical and risk-intensive sectors.