Agentic AI Developer
AI Tools
Tech Stack
Agent Workflow
Architect multi-agent orchestration using models like Gemini, Claude, LLaMA, and Mistral. Develop agent roles, memory systems, and inter-agent communication protocols. Implement RAG pipelines using vector databases. Create self-directed AI agents for workflow automation, knowledge retrieval, and multi-step reasoning.
About the Role
Capgemini is hiring a Full Stack Agentic AI Developer responsible for designing, developing, and deploying end-to-end agentic AI systems, combining AI engineering, software development, and system integration expertise. The role involves working with data scientists, backend engineers, and product teams to create self-directed AI agents capable of handling complex tasks such as workflow automation, knowledge retrieval, and multi-step reasoning.
Key Responsibilities
- GenAI & Multi-Agent Engineering: Architect and implement multi-agent orchestration frameworks using GenAI models like Gemini, Claude, LLaMA, and Mistral. Develop agent roles, memory systems, and inter-agent communication protocols. Integrate orchestration platforms including LangChain, CrewAI, and AutoGen with Google Vertex AI and Agent Builder.
- Prompt Engineering: Design high-quality prompts for agentic tasks, implement RAG pipelines using vector databases (FAISS, Pinecone, Weaviate), and optimize for accuracy and latency.
- Backend Development: Build RESTful APIs using Python (FastAPI, Flask) or Node.js on GCP infrastructure.
- Cloud & DevOps: Deploy on Google Cloud Platform with CI/CD pipelines, Terraform, Docker, and Kubernetes.
Required Skills
- SQL & Python programming
- GenAI frameworks (LangChain, LangGraph, Hugging Face, OpenAI API)
- LLM orchestration and agentic workflows
- Backend frameworks (FastAPI, Flask, Node.js)
- Vertex AI, Agent Builder, Google Cloud Functions
- Frontend knowledge (React, Next.js)
- Vector databases and RAG techniques
- Cloud platforms (AWS SageMaker, Azure AI, GCP)
Posted: March 25, 2026. Location: Stockholm, Sweden.