Data Scientist

TekFriday Processing Solutions Pvt Ltd; Hyderabad; On-site; INR 1,400,000 - 1,900,000; Full time

Job summary

TekFriday Processing Solutions Pvt Ltd in Hyderabad is seeking a data scientist to build, validate, and deploy real-time credit risk and fraud detection models to support underwriting decisions. You will work with large imbalanced datasets, develop thin-file models, optimize underwriting strategies, and design A/B experiments while ensuring risk thresholds are met and business growth is supported.

Experience with SQL/Snowflake, Python, ML lifecycles and cloud AWS will help you collaborate across

Qualifications

• 2–5 years of experience in credit risk analytics, lending analytics, or fintech data science.
• Master’s degree in a quantitative field.
• Hands-on experience in statistical modeling, machine learning, and predictive analytics.
• Experience with messy, real-world datasets and large-scale data processing.
• Exposure to cloud environments (AWS) and data engineering workflows.

Responsibilities

• Build, validate, and deploy real-time credit risk and fraud detection models to support underwriting decisions.
• Work with large-scale, imbalanced datasets to extract meaningful risk insights.
• Develop thin-file / new-to-credit models using alternative data sources.
• Optimize underwriting strategies including approval rates, credit limits, and pricing decisions.
• Design and execute A/B experiments to improve portfolio performance while maintaining risk thresholds.
• Continuously monitor model performance, stability, and drift; recommend recalibration strategies.
• Collaborate with Product, Engineering, and Growth teams to integrate models into scalable APIs and decision systems.
• Build and maintain automated data pipelines and model retraining workflows.
• Balance risk vs. growth, aligning with business objectives in fintech lending.
• Translate complex analytical outputs into clear business recommendations for stakeholders.

Skills

Credit risk analytics

Lending analytics

Fintech data science

Statistical modeling

Machine learning

Predictive analytics

Data processing

Data pipelines

Cloud AWS

Model governance

SHAP explainability

SQL

Snowflake

Python

Pandas

NumPy

Scikit-learn

Tableau

API integration

ML lifecycle

Education

Master’s degree in quantitative field

Tools

Snowflake

Tableau

AWS

Python

Git

Job description

TekFriday Processing Solutions | Full time

What we expect you to do:

• Build, validate, and deploy real-time credit risk and fraud detection models tosupport underwriting decisions
• Work with large-scale, imbalanced datasets to extract meaningful risk insights
• Develop thin-file / new-to-credit models using alternative data sources (mobile,transactional, behavioural signals)
• Optimize credit underwriting strategies including approval rates, credit limits,and pricing decisions
• Design and execute A/B experiments to improve portfolio performance whilemaintaining risk thresholds
• Continuously monitor model performance, stability, and drift; recommendrecalibration strategies
• Collaborate with Product, Engineering, and Growth teams to integrate modelsinto scalable APIs and decision systems
• Build and maintain automated data pipelines and model retraining workflows
• Balance risk vs. growth trade-offs, aligning with business objectives in a fintechlending environment
• Translate complex analytical outputs into clear business recommendations forstakeholders

Requirements

What you bring to the table:

• 2–5 years of experience in credit risk analytics, lending analytics, or fintech datascience.
• Master’s degree in a quantitative field such as Statistics, Computer Science,Economics, Applied Mathematics, or related discipline.
• Hands-on experience in statistical modeling, machine learning, and predictiveanalytics.
• Strong ability to work with messy, real-world datasets (incomplete, noisy, biased)and large-scale data processing.
• Experience in small business lending, fintech, or alternative credit ecosystems.
• Familiarity with model governance, validation frameworks, and explainabilitytechniques (e.g., SHAP).
• Exposure to cloud environments (AWS) and modern data engineering workflows.

Technical Skills Required:

• SQL & Snowflake for data extraction, transformation, and large-scale querying.
• Python for modeling, automation, and data analysis (Pandas, NumPy, Scikitlearn, etc.).
• Tableau (or similar BI tools) for data visualization and stakeholder reporting.
• Understanding of ML lifecycle (training, validation, deployment, monitoring).
• Exposure to API integration and production-level model deployment.