Associate Data Science

You will be part of NPCI’s Market Innovation team, working at the intersection of advanced machine learning, deep learning, graph AI, and Generative AI to build next-generation intelligent systems for India’s digital payments ecosystem.

This role focuses on solving India-scale problems such as fraud detection, mule/AML risk modeling, transaction intelligence, and conversational AI, using both classical ML and cutting-edge AI architectures (LLMs, GNNs, Transformers, Agentic AI systems).

You will design end-to-end AI systems—from problem formulation, feature engineering, and model development to GPU-accelerated optimization and production deployment, ensuring low latency, scalability, and robustness.

The role offers a unique opportunity to work on:

• Graph-based fraud detection systems
  
• Agentic AI & LLM-powered platforms (RAG, MCP, workflows)
  
• GPU/CUDA optimized AI pipelines
  
• Privacy-preserving and federated AI systems
  

You will collaborate with top academic institutions (IITs/IISc) and cross-functional teams to push the boundaries of applied AI in financial systems.

• Job Title: Data Scientist – AI Engineer
  
• Division: NPCI Data Analytics – Market Innovation
  
• Education: B.Tech / M.Tech / MSc / MCA (PhD preferred) in CS, AI, DS, Mathematics or related field
  
• Employment Type: Full-time
  
• Location: Hyderabad
  
• Role Type: Permanent
  

• Develop and deploy ML/DL models (Logistic Regression, RF, XGBoost, NN, CNN, Transformers, GANs)
  
• Build models for fraud detection, AML, anomaly detection, transaction intelligence
  
• Work on imbalanced datasets using advanced sampling and cost-sensitive learning
  

• Design Graph AI models: GNN, GCN, GAT, temporal graph networks
  
• Apply network analytics for fraud rings, mule detection, behavioral risk signals
  

• Build LLM-powered applications (chatbots, complaint intelligence, document analysis)
  
• Implement:
  
  • RAG pipelines
    
  • Agentic workflows & MCP (Model Context Protocols)
    
  • Prompt engineering & LLM fine-tuning
    

• Perform EDA, feature engineering (temporal, behavioral, aggregated features)
  
• Work with structured, semi-structured, and unstructured data
  

• Optimize models for:
  
  • Latency & throughput
    
  • GPU performance (CUDA-based optimization)
    
• Use libraries such as:
  
  • RAPIDS, cuDF, cuML, cuGraph, PyTorch Geometric
    

• Design custom loss functions (weighted BCE, cost-sensitive)
  
• Apply business-aligned metrics:
  
  • Precision@K, Recall, ROC-AUC, PR-AUC
    
• Use robust validation techniques (cross-validation, time-based splits)
  

• Integrate models into batch and real-time production systems
  
• Design scalable ML pipelines & APIs
  
• Monitor:
  
  • Model drift
    
  • Performance stability
    
  • Business impact
    

• Work with data engineers, product teams, and business stakeholders
  
• Contribute to research, innovation, and academic collaborations
  
• Stay updated on latest AI advancements (LLMs, Graph AI, Federated Learning)