Fullstack Gen AI Developer

Capgemini is a global leader in partnering with companies to transform and manage their business by harnessing the power of technology. The Group has over 360,000 team members globally in more than 50 countries. Capgemini combines strategic, creative, and scientific capabilities to deliver cutting-edge solutions, focusing on cloud, data, AI, connectivity, software, digital engineering, and platforms.

• Passion for Generative AI and fullstack development with hands-on experience delivering AI-powered web applications.
• Minimum 2 years of experience in software development covering both frontend and backend.
• Strong programming skills in Python and JavaScript/TypeScript with experience in FastAPI, Flask, Node.js, React, Next.js.
• Working knowledge of large language models (LLMs), prompt engineering, fine-tuning, and retrieval-augmented generation (RAG).
• Experience connecting to GenAI APIs and managing vector databases such as FAISS, Pinecone, Weaviate.
• Familiarity with cloud platforms (AWS, Azure, GCP) and CI/CD pipelines for deploying AI-driven applications.
• Understanding of data pipelines, embeddings, and model-serving infrastructure.
• Strong communication skills in English; German or Polish are a plus.

Nice to have:

• Experience with LangChain, LangGraph, OpenAI Function Calling, or custom agent frameworks.
• Familiarity with Vercel AI SDK, Next.js Server Actions, or other GenAI-focused web stacks.
• Background in UX for AI applications, multimodal systems, or real-time AI interfaces such as chat or co-creation tools.
• Experience building end-to-end prototypes or AI SaaS products from concept to production.

• Design, build, and deploy fullstack Generative AI applications, integrating advanced LLMs, image, and multimodal models into scalable products.
• Develop and maintain both frontend interfaces (React, Next.js) and backend systems (Python, Node.js) that power GenAI features.
• Implement AI-driven workflows including prompt orchestration, retrieval-augmented generation (RAG) pipelines, and real-time model interactions.
• Integrate foundation models and APIs (OpenAI, Anthropic, Hugging Face, Stability) into robust backend services and interactive user experiences.
• Collaborate closely with data scientists and product teams to translate business requirements into AI-enabled digital experiences.
• Ensure system scalability, performance, and security, leveraging cloud infrastructure and MLOps best practices.
• Stay at the forefront of GenAI innovations, experimenting with new models, frameworks, and architectures.