We are looking for a senior Data Scientist / ML Engineer with strong expertise in credit risk modelling, predictive analytics, and machine learning. The role will work closely with clients and business stakeholders to understand requirements, design analytical solutions, and develop, validate, deploy, and continuously improve credit risk models, with strong exposure to IFRS 9 requirements.

Key Responsibilities :

- Engage with clients and business stakeholders to understand requirements, define analytical problems, and brainstorm appropriate data science and modelling solutions.

- Design, develop, validate, deploy, and maintain credit risk and predictive models.

- Apply statistical and machine learning techniques to analyse large datasets, identify trends, risk factors, and patterns, and generate actionable insights.

- Develop analytical approaches aligned with business objectives, hypotheses, and risk management requirements.

- Independently solve complex analytical and modelling problems and translate findings into meaningful business recommendations.

- Work on IFRS 9 credit risk models, including expected credit loss (ECL) modelling and related regulatory requirements.

- Develop and evaluate predictive models using Python and R, applying appropriate statistical and machine learning methodologies.

- Work with structured and unstructured data, including text data, with experience in text cleaning, TF-IDF, vectorization, and related NLP techniques.

- Design and conduct experiments and prototypes using new machine learning algorithms, modelling techniques, and prediction approaches.

- Implement robust model development, testing, deployment, monitoring, and maintenance practices.

- Collaborate with Product Managers, Business Analysts, Data Scientists, and other stakeholders to translate business problems into scalable analytical solutions.

- Ensure adherence to machine learning and model development best practices, including data quality, validation, documentation, reproducibility, and model performance.

- Continuously evaluate and improve existing models and analytical approaches based on business outcomes and changing risk requirements.

- Stay updated on developments in credit risk modelling, machine learning, statistical techniques, IFRS 9, and regulatory expectations.

Required Candidate Profile :

- 8 - 12 years of experience in Data Science, Machine Learning, Predictive Modelling, or Credit Risk Analytics.

- Strong hands-on expertise in Python and machine learning/predictive modelling.

- Strong experience in credit risk modelling, preferably across retail, consumer, commercial, or banking/financial services portfolios.

- Hands-on experience with IFRS 9 models and related regulatory requirements is mandatory.

- Strong understanding of statistical modelling, machine learning algorithms, model validation, and predictive analytics.

- Proficiency in R programming and experience applying advanced statistical techniques.

- Experience analysing large and complex datasets and translating analytical findings into business insights.

- Hands-on experience with unstructured/text data, including text cleaning, TF-IDF, text vectorization, and NLP techniques.

- Experience in designing, testing, deploying, and maintaining machine learning solutions in production environments.

- Strong client-facing and stakeholder management skills, with the ability to independently understand requirements and communicate technical solutions.

- Strong problem-solving, analytical, communication, and presentation skills.

- Experience in banking, NBFC, financial services, or risk analytics is strongly preferred.