The Opportunity

You will be part of NPCIs Market Innovation & AI Engineering team, driving the development of next-generation Machine Learning and Deep Learning systems powering Indias largest digital payments ecosystem.

This role focuses on solving large-scale real-world problems using advanced Machine Learning, Statistical Modeling, Deep Learning, Graph Analytics, and Distributed AI Systems. You will be responsible for designing, building, and scaling production-grade AI platforms that process billions of transactions while maintaining high standards of latency, reliability, explainability, and operational excellence.

The role offers a unique opportunity to work on:

• Fraud Detection & Risk Modeling
  
• AML & Financial Crime Analytics
  
• Behavioral Intelligence Systems
  
• Transaction Intelligence Platforms
  
• Large Scale Anomaly Detection Systems
  
• Graph-based Network Analytics
  
• Real-Time Decisioning Systems
  
• GPU Accelerated AI Workloads
  

You will collaborate closely with engineering teams, data platform teams, domain experts, and leading academic institutions to build cutting-edge AI solutions for large-scale financial ecosystems.

Job Details

Key Responsibilities

Machine Learning & Advanced Modeling

• Design, develop, and deploy advanced Machine Learning solutions using supervised and unsupervised learning techniques.
  
• Build and optimize predictive models for fraud detection, anomaly detection, transaction intelligence, risk scoring, and behavioral analytics.
  
• Develop robust feature engineering frameworks for large-scale transactional datasets.
  
• Design custom evaluation methodologies and business-aligned performance metrics.
  
• Build explainable and interpretable AI systems for regulated environments.
  

Deep Learning Systems

• Develop Deep Learning models utilizing Neural Networks, CNNs, RNNs, LSTMs, Autoencoders, Transformers, and Representation Learning techniques.
  
• Optimize model architectures for production deployment and inference efficiency.
  
• Design custom loss functions and optimization strategies for imbalanced datasets and complex business problems.
  

Production AI & MLOps

• Design and implement scalable ML deployment pipelines.
  
• Productionize Machine Learning models using containerized infrastructure.
  
• Develop automated CI/CD workflows for model deployment and version management.
  
• Implement model monitoring, drift detection, performance tracking, and rollback mechanisms.
  

AI Platform Engineering

• Build high-throughput, low-latency inference platforms capable of supporting large transaction volumes.
  
• Design feature engineering and feature serving architectures for real-time prediction use cases.
  
• Collaborate with platform teams to optimize compute, storage, and data access layers.
  

Distributed AI Systems

• Develop machine learning workflows for large-scale datasets utilizing distributed computing frameworks.
  
• Build scalable data processing pipelines capable of handling billions of events and transactions.
  
• Optimize training and inference workloads across multi-node environments.
  

Research & Innovation

• Evaluate emerging techniques in Machine Learning and Deep Learning.
  
• Contribute to innovative solutions, intellectual property creation, technical whitepapers, and research publications.
  
• Collaborate with academic partners and industry experts on advanced AI initiatives.
  

Required Technical Skills

Core Machine Learning

• Strong understanding of:
  
  • Supervised Learning
    
  • Unsupervised Learning
    
  • Ensemble Learning
    
  • Statistical Learning
    
  • Reinforcement Learning Fundamentals
    
  • Classification & Regression Techniques
    
  • Anomaly Detection
    
  • Time Series Forecasting
    

Mathematics & Statistics

• Probability Theory
  
• Inferential Statistics
  
• Hypothesis Testing
  
• Bayesian Statistics
  
• Optimization Techniques
  
• Linear Algebra
  
• Calculus for Machine Learning
  

Deep Learning

• Artificial Neural Networks (ANN)
  
• CNN
  
• RNN
  
• LSTM
  
• GRU
  
• Autoencoders
  
• Representation Learning
  
• Transformers
  
• Model Optimization Techniques
  

Programming & Data Engineering

• Python
  
• NumPy
  
• Pandas
  
• Scikit-Learn
  
• SQL
  
• PySpark
  

Deep Learning Frameworks

• PyTorch
  
• TensorFlow
  
• Keras
  

Production AI & MLOps

• MLOps
  
• MLflow
  
• Kubeflow
  
• Model Registry
  
• Feature Store Concepts
  
• Model Monitoring
  

Containerization & Orchestration

• Docker
  
• Kubernetes
  
• Helm
  

Distributed Processing

• Apache Spark
  
• Distributed Training Frameworks
  
• Parallel Data Processing Systems
  

System Design

• Scalable AI Architecture
  
• Distributed Systems Design
  
• Performance Engineering
  
• Reliability Engineering
  
• Latency Optimization
  
• Observability & Monitoring
  

Good to Have Skills and Experience Required

Advanced AI Infrastructure

• GPU Computing
  
• CUDA
  
• NVIDIA RAPIDS
  
• TensorRT
  
• Distributed GPU Training
  

Big Data Ecosystem

• Hadoop
  
• Kafka
  
• Flink
  
• Trino
  
• MinIO
  

Platform Engineering

• CI/CD Pipelines
  
• GitHub Actions
  
• Jenkins
  
• ArgoCD
  
• GitLab CI/CD
  

Advanced Analytics

• Graph Analytics
  
• Network Analysis
  
• Fraud Network Detection
  
• Entity Resolution
  

Research & Innovation

• Publications in IEEE, ACM or reputed AI/ML conferences
  
• Patent filings or innovation contributions
  
• Experience designing custom loss functions and optimization algorithms
  
• Experience solving large-scale real-world AI problems