Senior Developer Account Analytics at Publicis Groupe in IN-KA-Bengaluru

Job description

• Powerful predictors of the future - our Analytics team seamlessly blends data science and business intelligence to provide unparalleled foresight for our platform offerings. They turn insights into actionable results for our clients by collaborating with senior team members and staying ahead of market trends, powered by our data assets. By using new-age analytic tools and emerging technologies, the team cultivates a dynamic learning environment for curious minds to thrive.
• The Senior Developer is a builder. You will write the code behind our AI capabilities: agents, knowledge systems, and analytical applications used by analysts on live client work. This is a small team where the person who designs a component is usually the person who ships it, and where what you build reaches users in weeks rather than quarters.
• We already run AI agents in production that generate analyst-grade SQL against our analytics environment. You will help extend that foundation into harder territory.
• Interpretation. Systems that take the output of an analysis and produce business-relevant interpretation — what the numbers actually mean for a given client and category.
• Client knowledge. A knowledge system that accumulates what the organization understands about each client and makes it retrievable by both people and agents.
• Media Investment planning. Analytical tooling that supports budget allocation and media investment planning decisions.
• Click here to view how Epsilon transforms marketing with 1 View, 1 Vision and 1 Voice.

Responsibilities

• Building
• Design, build, test, and maintain the applications, agents, and automation that the Account Analytics organization runs on.
• Write clean, reviewed, documented code that another engineer can pick up and extend.
• Build integrations across data platforms, APIs, internal services, and reporting systems.
• Own components end to end — from design discussion through deployment and the support that follows it.
• AI Engineering
• Implement LLM-based components: agents, tool interfaces, structured outputs, and the orchestration that connects them.
• Build and run the evaluation harnesses that tell us whether a change improved an agent or merely changed it. Non-deterministic systems need tests too, and building them is part of the job rather than an afterthought.
• Implement context and retrieval strategies, and contribute evidence to the decisions about which approach fits a given problem.
• Prototype quickly when a question is better answered by code than by discussion.
• Collaboration
• Work with analysts and client teams to understand what a tool has to do before deciding how it will do it.
• Participate substantively in design and code review, as author and as reviewer.
• Contribute to the team's standards and to the documentation that makes them stick.

Requirements

• 5+ years building and maintaining production software or data applications.
• Strong Python and SQL. You have worked in a real codebase with other engineers, not only in notebooks or scripts.
• Hands-on experience building with LLMs — prompting, tool use, agent frameworks, structured output — with something you shipped and can talk through in detail.
• Fluent with Git and collaborative development practice: branching, review, testing, deployment.
• Strong analytical and problem-solving ability, and the instinct to ask what a piece of output means rather than only whether the code ran.
• Clear written communication. Much of this team's collaboration happens in writing and across time zones.
• Bachelor's degree in Computer Science, Engineering, Data Science, Mathematics, Statistics, or a related discipline.
• Agentic development environments — Claude Code, Cursor, GitHub Copilot, or similar — used as a daily working tool.
• Databricks, Greenplum or PostgreSQL, Snowflake, BigQuery, or comparable analytical platforms.
• Retrieval-augmented generation, embedding stores, and context management approaches.
• Cloud platforms (Azure, AWS, GCP) and CI/CD pipelines.
• Evaluation frameworks or testing approaches for LLM applications.
• Tableau, Power BI, or related visualization tools.
• Exposure to marketing measurement concepts — attribution, incrementality, campaign performance analysis. Useful, and learnable here if you are curious about it.

Skills

Required

• Python
• SQL
• Git
• Analytical and problem-solving ability
• Clear written communication

Preferred

• Cloud platforms (Azure, AWS, GCP)
• CI/CD pipelines
• Tableau, Power BI