GEN AI
Capgemini Engineering
Gurgaon, Haryana, India3h agovia LinkedIn
Posted 20 Nov 2026, 22:50 IST
This job at a glance
Capgemini Engineering is hiring for GEN AI (on-site in Gurgaon). It is open to freshers. The posting asks for Product management and Stakeholder management. 26% of the 99 similar fresher jobs posted this week also ask for Stakeholder management. Pay is not stated.
- Who can apply
- Freshers
- Must know
- Product managementStakeholder management
- Work
- On-site in Gurgaon
- Pay
- Not stated by the employer.
- Skill demand
- Stakeholder management26%Product management9%of 99 similar fresher jobs posted in India this week
- Listed
- 20 Nov 2026 · still open
Sign in free to see which of these skills your resume already shows.
From the original posting on LinkedIn
About the Role
Capgemini Engineering is seeking individuals to build hands-on Gen AI prototypes, pilots, and reusable components for their AI roadmap.
Key Responsibilities
- Implement AI solutions for:
- Knowledge-base query
- Requirements generation
- Design support
- Trace/RCA
- Test strategy
- Test case generation
- Test execution support
- Deployment/MOP
- Stakeholder interaction analysis
- Develop RAG pipelines over requirements specifications, design documents, test plans, tickets, KB articles, deployment records, application and system logs, and traces.
- Build document-processing pipelines including parsing, metadata extraction, chunking, embedding generation, vector indexing, and retrieval logic.
- Create prompts, structured outputs, and reusable skill files for requirements, acceptance criteria, design summaries, test cases, RCA summaries, and stakeholder summaries.
- Build n8n workflows for AI automation, including document ingestion, knowledge refresh, ticket summarization, requirement extraction, trace processing, test generation, approvals, and metrics capture.
- Use Claude Code to support code understanding, code generation, refactoring, unit-test generation, documentation, and engineering productivity.
- Implement evaluation mechanisms to track output quality, retrieval accuracy, hallucination risk, human review effort, time saved, adoption, and AI output acceptance rate.
- Collaborate closely with SMEs, developers, testers, deployment teams, and use-case owners to validate AI outputs and improve solution quality.
- Document reusable assets, demos, workflows, lessons learned, and implementation patterns in the AI KM repository and AI Engineering Playbook.
Requirements & Tech Stack
- Gen AI
- AI Solutions
- RAG pipelines
- Document processing
- Claude Code
- n8n workflows
- Vector indexing
- AI KM repository
- AI Engineering Playbook