Risk Analyst (Data) || Mobikwik || Gurugram

MobiKwik is Indias leading Digital Financial Services platform & Largest Digital Wallet, trusted by over 167 million users & 4.4 million businesses. As a pioneer in the Fintech space, MobiKwik empowers its users with a robust suite of services, including Digital payments, Credit & Investments. Recently, MobiKwik achieved a significant milestone with its Initial Public Offering (IPO), marking a new chapter in its journey of innovation & growth.

With a mission to democratize financial inclusion, MobiKwik continues to transform how Indians manage their money, offering secure, seamless & user-friendly solutions that cater to a diverse range of financial needs.

About the Role

We are looking for a Data Analyst / Senior Data Analyst-Risk Analytics to build and scale data-driven risk intelligence, including Early Warning Systems (EWS), predictive models, simulations, and scorecards. This role sits at the intersection of risk, data science, and AI, enabling real time, automated risk monitoring and decision-making across the organization.

Key Responsibilities:

1. EWS Model Development (Core Ownership)

• Design and build Early Warning System (EWS) models using regression models (linear, logistic) and classification models (tree based, ensemble methods).
• Identify leading risk indicators across transactions, customer behavior, and operational metrics.
• Define thresholds, triggers, and alert logic.
• Continuously refine models based on performance and feedback loops.

2. Risk Modeling, Scorecards & Simulations

• Build risk scorecards for customer risk, transaction risk / fraud signals, and operational risk scoring.
• Develop and run simulations / scenario analysis to assess potential risk outcomes and stress test models and thresholds.
• Apply statistical and machine learning techniques to improve predictive accuracy.

3. Risk Analytics & Predictive Insights

• Develop anomaly detection frameworks.
• Perform trend analysis and pattern recognition.
• Translate data into actionable insights for ERM and ORM teams.

4. Data Pipeline & Engineering

• Build and manage end-to-end data pipelines (ETL/ELT).
• Ensure data quality, availability, and scalability.
• Integrate multiple data sources for real-time and batch processing.

5. SQL & Data Management

• Write efficient SQL queries on large datasets.
• Extract, transform, and analyze transactional and operational data.
• Support data-driven decision making across teams.

6. AI / LLM / Agentic AI Integration

• Work hands-on with Claude and other LLMs for risk signal extraction from unstructured data and incident summarization and classification.
• Build Agentic AI workflows for automated EWS alerts, intelligent monitoring and escalation.
• Ensure secure and compliant AI deployment.

7. Data-Driven Risk Monitoring Platform

• Build and enhance risk monitoring dashboards and platforms.
• Enable near real-time visibility of risk indicators.
• Implement automated alerts and exception reporting systems.

8. Stakeholder Collaboration

• Work closely with ERM (EWS design & thresholds), ORM (incident & control data), and Product & Tech (data pipelines & system integration).
• Translate business problems into scalable analytical solutions.

Key Skills & Requirements:

Data Science & Modeling

• Strong foundation in regression (linear, logistic) and classification (decision trees, ensemble methods).
• Hands-on experience in scorecard development, simulations / scenario analysis / stress testing, and anomaly detection / predictive modeling.

Technical Skills (Mandatory)

• Strong proficiency in Python (Pandas, NumPy, Scikit-learn, etc.).
• Advanced SQL skills.
• Experience in building data pipelines (ETL / ELT frameworks).

AI & Emerging Tech

• Hands-on experience with Claude or similar LLMs.
• Understanding of Agentic AI / workflow automation.
• Exposure to LLM-based analytics and reasoning workflows.

Core Competencies

• Strong analytical and problem-solving skills.
• Ability to work with large datasets and complex systems.
• Strong communication and stakeholder management.

Success Metrics (KPIs):

• Accuracy and effectiveness of EWS models (precision, recall, early detection).
• Performance of risk scorecards and predictive models.
• Effectiveness of