Python Engineering AI Lead-Assistant Vice president

Citi; Chennai District; On-site; INR 3,000,000 - 6,000,000; Full time

Job summary

Citi in Chennai seeks a Principal Engineer to design and build scalable data pipelines for Retail and Wealth Risk Engineering, leveraging AI and big-data tech to support AI agent deployment, analytics, and data engineering.

You will lead enterprise-grade ELT/ETL with PySpark, Kafka, Databricks, and cloud-native infrastructure, ensuring data quality, security, and compliance while advancing Data Mesh architectures.

Qualifications

• 8+ years in large-scale application development with a focus on secure AI agent deployment.
• 5+ years leading Python and PySpark engineering for enterprise ELT/ETL in Databricks ecosystem.
• Hands-on with YAML/JSON, FAST API, Google ADK, LLM integrations, and prompt engineering.
• Experience automating microservice integrations for data-intensive apps.
• Proficient in Python or Scala and strong SQL skills.
• Knowledge of data modeling, Data Mesh, and data federation; cross-team collaboration.

Responsibilities

• Design, develop, and maintain AI agents and ELT/ETL using PySpark, Kafka, and Databricks.
• Build and deploy GPT-based AI agents to support automation and human-in-the-loop workflows.
• Create data federation layers for Lambda and Data Mesh architectures; leverage Starburst.
• Develop microservice integrations with cloud-native infra and CI/CD pipelines.
• Leverage agentic AI tools and platforms via advanced prompt engineering for efficiency.
• Ensure data quality, integrity, and security across the data lifecycle.
• Improve data engineering standards and ensure compliance with laws and regulations.

Skills

Python

PySpark

SQL

Data Modeling

Cloud platforms

AI agent deployment

Kafka

Databricks

CI/CD

Prompt engineering

Education

Bachelor's degree in CS/Engineering

Master's degree is a plus

Tools

Google ADK

Kubernetes

Docker

Databricks

OpenShift

Starburst

FAST API

GCP/AWS/Azure

Job description

Job Summary

We are seeking a highly motivated and experienced Principal Engineer to join our Retail and Wealth Risk Engineering team under the Enterprise Risk Technology platform. The role focuses on designing, building, and maintaining robust, scalable data pipelines and solutions that leverage cutting-edge AI and big‑data technologies to support AI agent deployment, analytics, and data engineering.

Responsibilities

• Design, develop, and maintain scalable, enterprise‑grade AI agents and ELT/ETL processes using Python, FAST API, Microservices, PySpark, Kafka, and the Databricks ecosystem.
• Build and deploy GPT‑based AI agents using Google’s ADK and Google Flash 2.5+ LLMs to support application automation and workflow with Human‑in‑Loop architectures.
• Build and maintain data federation layers for Lambda and Data Mesh architectures using tools such as Starburst, while adopting AI‑based use cases to drive efficiency.
• Develop, deploy, and automate microservice integrations to support data‑intensive applications, ensuring scalability, resilience, and maintainability with cloud‑native infrastructure and OpenShift or Kubernetes, including CI/CD pipelines.
• Integrate and leverage agentic AI tools (e.g., Devin.AI, GitHub Copilot) and platforms (e.g., MCP) through advanced prompt engineering to enhance development and operational efficiency.
• Ensure data quality, integrity, and security throughout the data lifecycle.
• Contribute to continuous improvement of data engineering processes, standards, and best practices within the team.
• Assess risk in business decisions, uphold firm reputation, and safeguard Citi, its clients, and assets by driving compliance with applicable laws, rules, and regulations, while applying sound ethical judgment and reporting control issues with transparency.

Qualifications

• 8+ years of overall experience in large‑scale application development with a recent focus on secure AI agent deployment.
• 5+ years of proven experience leading Python and PySpark engineering for enterprise‑grade, high‑volume ELT/ETL processes using the PySpark and Databricks ecosystem.
• Hands‑on experience with agentic AI development using YAML, JSON, FAST API or Spring Boot, Google ADK, LLM integrations, and advanced prompt engineering.
• Proven experience developing and automating microservice integrations for data‑intensive applications.
• Proficiency in at least one data‑analytics programming language such as Python or Scala.
• Strong SQL skills and experience with relational databases.
• Deep understanding of data modeling, data warehousing concepts, Data Mesh architecture, and data federation.
• Excellent communication, collaboration, and problem‑solving skills.

Preferred Qualifications

• Experience with cloud‑based big‑data platforms (e.g., Cloudera, Databricks, AWS, Azure, GCP).
• Experience with front‑end technologies such as Angular or React JS for building data‑driven application interfaces.
• Practical experience applying AI/ML techniques to solve real‑world business problems.
• Familiarity with containerization technologies (e.g., Docker, Kubernetes).
• Experience in data engineering within banking retail product domains (e.g., cards, mortgage, deposits, wealth management).
• Relevant industry certifications (e.g., AWS Certified Big Data – Specialty, Azure Data Engineer Associate).

Education

• Bachelor’s degree in Computer Science, Engineering, or a related field.
• Master’s degree is a plus.

Equal Opportunity Employer

Citi is an equal opportunity employer, and qualified candidates will receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, status as a protected veteran, or any other characteristic protected by law.

If you are a person with a disability and need a reasonable accommodation to use our search tools and/or apply for a career opportunity, please review the accessibility resources available at Citi.

View Citi’s EEO policy statement and the Know Your Rights poster.