Data Analyst

This Chennai-based analytics role combines Python data analytics with generative AI to automate text analysis, summarisation, and knowledge extraction for business teams. You will collect and clean complex enterprise data, build reusable pipelines, and design generative AI workflows using advanced tooling like LangGraph, LangChain, and Model Context Protocol.

What you'll do

• Collect, clean and structure enterprise data with Python for reporting, forecasting and insights.
• Design robust Python data pipelines and reusable code for ingestion, transformation and validation.
• Build generative AI workflows using LLMs for text analysis, summarisation and knowledge extraction.
• Develop MCP-based integrations that manage prompts, context windows and tool connections.
• Build LangGraph workflows and LangChain chains/agents that securely connect models to internal data.
• Analyse large structured and unstructured datasets, set up data quality checks and document solutions.

What they ask for

• Engineering or science graduates with strong Python skills.
• Working knowledge of LLMs, prompt design and responsible AI practices.
• Hands-on projects with LangChain, LangGraph or agent frameworks.
• SQL and data-wrangling skills, plus clear communication with business stakeholders.
• Comfortable with a hybrid schedule in Chennai.

Good to have

• MCP exposure

Selection process

1. Resume shortlisting against Python and GenAI skills
2. Technical interview on Python, SQL and data analysis
3. GenAI deep-dive – LLM workflows, LangChain/LangGraph and a project walkthrough
4. HR discussion

Sign in or create a profile on Cognizant Careers, upload your resume with GitHub links to your Python and GenAI projects at the top, and submit.

Tap what's true for you. Your answers are saved for every other job too.

Put these words in your resume and practise these questions before the interview.

Technical

1. How do you handle memory and context management in LangChain chains or agents?
2. Can you explain how you would design a Python data pipeline to clean and structure messy enterprise datasets?
3. What are the differences between using LangGraph versus standard LangChain chains for multi-step workflows?

Scenario

1. What would you do if an LLM workflow started returning hallucinated or inconsistent outputs during text summarisation?
2. How would you approach optimizing a slow-running SQL query or Python data transformation script processing large unstructured datasets?

HR

1. Can you walk us through a complex GenAI project you built from scratch?
2. How do you manage shifting priorities when working with multiple business stakeholders in a hybrid environment?

About Cognizant

1. How do you think Cognizant leverages generative AI solutions to drive digital transformation for its enterprise clients?

Practice questions written from the job listing, not this company's real interview questions.

Applied here? Tell the next person what happened. It's anonymous and takes one tap.