Data Scientist

Job Title: Data Scientist

Location: Bengaluru, Gurgaon

Experience: 6-10 years

About the Company

We are an organization focused on data analytics and digital operations, with a strong presence in banking, fintech, financial services, and NBFC engagements. The team delivers high-impact analytics solutions that improve credit decisioning, fraud detection, and broader risk outcomes for leading financial services clients. This role sits within a confidential hiring process, so company identity is intentionally withheld. The environment is built around solving complex business problems through structured data, machine learning, and rigorous model governance. The work requires close collaboration with business and risk stakeholders to turn requirements into deployable analytical solutions that create measurable value.

About the Role

This role owns the development and deployment of machine learning solutions for credit risk and fraud use cases. The focus is on building accurate, scalable, and governed predictive models using structured data, with strong emphasis on end-to-end model delivery. The position requires deep hands-on experience in credit risk modeling, especially using XGBoost or Gradient Boosting, and the ability to translate business needs into robust analytical outcomes. Success depends on strong Python skills, statistical thinking, and practical judgment in model validation, monitoring, and optimization. The role partners closely with risk and business teams to support decisions that improve portfolio quality, reduce losses, and strengthen model performance.

Key Responsibilities

• Own the end-to-end lifecycle of credit risk and fraud models, from feature design to deployment readiness, so business teams can rely on measurable and governed decision support.
• Build predictive models on structured data using supervised learning methods, ensuring the solution improves scoring accuracy and supports scalable risk decisioning.
• Perform feature engineering, training, validation, monitoring, and optimization to keep model performance stable and aligned to business outcomes.
• Apply XGBoost and Gradient Boosting as primary modeling approaches for credit risk use cases, with practical use of other supervised algorithms where they improve performance.
• Work with large datasets to identify patterns, improve model lift, and convert raw data into insights that strengthen credit and fraud decisions.
• Collaborate with business and risk stakeholders to translate requirements into analytical solutions that are deployment-ready and aligned to governance standards.
• Ensure model documentation, validation evidence, and governance artifacts are complete so models can move smoothly through review and production processes.

Essential Skills & Technologies

• Strong Python programming skills with hands-on experience building, validating, and deploying machine learning models in production-oriented environments.
• Proven expertise in credit risk modeling using XGBoost or Gradient Boosting, with the ability to explain model behavior, performance, and business impact.
• Solid understanding of statistics, predictive analytics, feature engineering, and model evaluation techniques for supervised learning problems.
• Experience working with structured datasets and end-to-end model development across training, validation, monitoring, and optimization.
• Exposure to fraud modeling, Random Forest, and other supervised learning algorithms that improve prediction quality and operational usefulness.

Additional Plus

• Banking, FinTech, Financial Services, or NBFC domain experience that helps accelerate delivery in regulated lending and risk environments.
• Experience with model governance, documentation, and deployment processes in environments where auditability and control matter.
• Prior exposure to large-scale analytics delivery for financial services clients, especially where model outcomes influence credit and fraud decisions.

What You'll Bring

• 6-10 years of relevant experience in machine learning and data science, with deep credit risk modeling exposure.
• Strong practical ownership of XGBoost or Gradient Boosting based credit risk solutions, supported by sound statistical judgment and Python execution.
• Ability to work cross-functionally with risk and business teams, convert ambiguity into clear analytical direction, and deliver production-ready outcomes.
• A disciplined approach to model governance, documentation, and performance monitoring in a financial services context.

Why Join Us

Join a high-impact analytics environment where your models directly influence credit decisions, fraud prevention, and risk outcomes for leading financial services clients. You will work on meaningful use cases that require both technical depth and business judgment, with the opportunity to shape solutions that improve portfolio quality and operational effectiveness. The role offers exposure to complex financial datasets, rigorous model governance, and collaborative problem-solving across business and risk stakeholders. If you want to build practical machine learning solutions that matter in regulated environments, this is a strong opportunity to do that at scale.

What We Offer

• Opportunity to work on high-impact credit risk and fraud analytics projects for leading banking and financial services clients.
• A collaborative environment that values rigorous model development, governance, and deployment readiness.
• Exposure to complex, business-critical use cases where strong analytics directly improves decision-making and risk outcomes.