Lead Data Scientist (Fraud, Payments)

AI/ML Data Scientist

Location: Bangalore (Hybrid)

Experience: 8-15 Years

Industry: Payments / FinTech

About Company

Altimetrik is a global AI-native engineering and digital transformation company headquartered in Southfield, Michigan, USA. Founded in 2012, the company helps enterprises modernize their technology, data, and business operations through artificial intelligence, cloud, data engineering, product engineering, and digital solutions

About the Role

We are seeking an experienced AI/ML Data Scientist to design, build, and deploy machine learning solutions for large-scale payment platforms. The ideal candidate will leverage advanced analytics, machine learning, and AI technologies to address business-critical challenges including fraud detection, risk scoring, authorization optimization, anomaly detection, and transaction monitoring.

This role combines expertise in Data Science, Machine Learning Engineering, and the Payments domain, working closely with Product, Risk, Compliance, and Engineering teams to develop production-grade AI solutions that drive business outcomes.

Key Responsibilities

Machine Learning & Model Development

• Design, develop, validate, and deploy ML models for:
• Real-time fraud detection
• Card-not-present (CNP) risk scoring
• Authorization approval/decline optimization
• Merchant risk assessment
• Chargeback and dispute prediction
• AML and transaction anomaly detection
• Build advanced features using transactional, behavioral, device, and network data.
• Select and implement appropriate ML techniques including classification, anomaly detection, graph analytics, time-series modeling, and deep learning.

MLOps & Production Engineering

• Deploy machine learning models in real-time and batch processing environments.
• Implement model monitoring, drift detection, performance tracking, and retraining strategies.
• Establish MLOps best practices including model versioning, CI/CD pipelines, reproducible training workflows, and A/B testing frameworks.
• Collaborate with engineering teams to ensure scalability, reliability, and low-latency model performance.

AI & Generative AI Applications

• Utilize modern AI and LLM technologies (Claude, GPT, etc.) to enhance data science workflows.
• Develop AI-driven solutions for feature discovery, automated reporting, anomaly interpretation, and analyst productivity.
• Explore GenAI use cases within Risk, Fraud, and Compliance functions while ensuring appropriate governance.

Stakeholder Collaboration & Governance

• Partner with Fraud, Risk, Compliance, Product, and Engineering teams to deliver explainable and auditable AI solutions.
• Present analytical insights and model performance to business stakeholders and leadership teams.
• Ensure compliance with PCI-DSS, data privacy regulations, and enterprise data governance standards.

Required Skills & Qualifications

• 10+ years of overall IT experience with at least 3+ years in Data Science or Machine Learning roles.
• Strong expertise in:
• Python (Pandas, Scikit-learn, XGBoost, LightGBM, TensorFlow, PyTorch)
• SQL
• Machine Learning Algorithms
• Statistical Modeling
• Anomaly Detection
• Hands-on experience deploying ML models into production environments.
• Strong understanding of imbalanced datasets and fraud detection techniques.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Exposure to big data technologies including Spark, Airflow, Databricks, or similar tools.
• Knowledge of financial services regulations, data security, and compliance frameworks.
• Excellent communication and stakeholder management skills.

Preferred Qualifications

• Experience within Payments, FinTech, Banking, or Financial Services industries.
• Knowledge of payment fraud typologies such as:
• Card-Not-Present (CNP) Fraud
• Account Takeover
• Synthetic Identity Fraud
• BIN Attacks
• Card Testing Fraud
• Experience with graph-based fraud detection and network analytics.
• Familiarity with Visa and Mastercard risk management frameworks.
• Hands-on exposure to Generative AI and LLM applications in enterprise environments.
• Experience working with streaming platforms such as Kafka or Flink.
• Masters or PhD in Computer Science, Statistics, Mathematics, Data Science, or related quantitative disciplines.