Lead Data Scientist

Careernet; Chennai District, Bengaluru; On-site; INR 3,500,000 - 6,000,000; Full time

Job summary

Careernet is seeking a senior data scientist to develop fraud detection, risk analytics, and ML models for high-volume financial activity in Chennai. The role emphasizes building robust data pipelines, feature engineering, and validating models for production use.

You will collaborate with engineering and risk teams to operationalize models, monitor outcomes, and improve accuracy over time, while supporting API integrations and cloud-based workflows.

Qualifications

• 6–10 years in data science or analytics engineering.
• Proficient Python and SQL for data work.
• Strong fraud analytics and ML modeling background.
• Experience with production pipelines, validation, and monitoring.
• Ability to support API integrations, CI/CD, and cloud analytics.

Responsibilities

• Develop fraud detection, anomaly detection, and risk scoring models for high-volume transaction and account activity.
• Design feature engineering and validation for structured, time-based, and relationship-driven fraud signals.
• Build and maintain ETL/ELT pipelines that support model training, scoring, and analytics workflows.
• Integrate REST APIs and external data sources into production analytics and decisioning processes.
• Partner with engineering and risk teams to operationalize models, monitor outcomes, and improve model quality over time.

Skills

Risk Analytics

Data Scientist

Fraud Analysis

Python

Machine Learning

SQL

Education

Bachelor's degree in data science / related field

Master's degree preferred

Tools

Snowflake

PostgreSQL

Neo4j

Cypher

MLOps

Azure

AWS

Kubernetes

Observability tools

Fraud case-management experience

Job description

Key Skills: Risk Analytics, Data Scientist, Fraud Analysis, Python,Machine Learning, SQL

Roles and Responsibilities:

• Develop fraud detection, anomaly detection, and risk scoring models for high-volume transaction and account activity.
• Design feature engineering and validation approaches for structured, time-based, and relationship-driven fraud signals.
• Build and maintain ETL/ELT pipelines that support model training, scoring, and analytics workflows.
• Integrate REST APIs and external data sources into production analytics and decisioning processes.
• Partner with engineering and risk teams to operationalize models, monitor outcomes, and improve model quality over time.

Skills Required:

• 6-10 years of experience in data science, analytics engineering, machine learning, or a closely related discipline.
• Advanced hands-on experience in Python and SQL for data science and analytics engineering work.
• Strong background in fraud analysis, risk analytics, machine learning, and statistical modeling.
• Experience with production-grade data pipelines, model validation, and model monitoring on large datasets.
• Ability to support API integrations, CI/CD practices, and cloud-based analytical environments.

Good to Have:

• Snowflake, PostgreSQL, Neo4j, Cypher, MLOps, Azure, AWS, Kubernetes, observability tools, and fraud case-management experience.

Education: Bachelor's degree in data science, computer science, engineering, statistics, mathematics, operations research, or a related quantitative field; Master's degree preferred.