GenAI Engineer

Role Overview

At Capgemini Invent, we believe difference drives change. As inventive transformation consultants, we blend our strategic, creative and scientific capabilities, collaborating closely with clients to deliver cutting-edge solutions. We are seeking a skilled OpenAI Developer to join our dynamic team. The ideal candidate will have a robust understanding of AI and machine learning, with particular expertise in integrating OpenAI models with Microsoft's Power Platform (including Power Automate and Power Virtual Agents), Azure Cognitive Services, and agentic AI frameworks. This role also requires experience in Azure deployment of AI solutions and modern Autogen-based architectures for building intelligent multi-agent systems.

Responsibilities

• Design, develop, and optimize OpenAI-powered applications, including multi-agent frameworks, chatbots, and AI-based customer support systems.
• Leverage agentic technologies (e.g., Autogen framework) to implement AI agents capable of collaborating and completing complex tasks autonomously.
• Build and maintain backend services using Python or .NET to support OpenAI integrations.
• Work with custom datasets, applying techniques such as chunking, embedding, and vector search for model fine-tuning and retrieval-augmented generation (RAG).
• Integrate Azure Cognitive Services (e.g., Text Analytics, Translator, Form Recognizer) to enhance functionality and intelligence of AI solutions.
• Ensure scalable and secure deployment of AI solutions on Azure, using services like Azure Functions, Azure App Service, and Azure Kubernetes Service (AKS).

Requirements

• Bachelor's degree in Computer Science, Engineering, or related field.
• 6 years + in Python or .NET for backend and AI integration development. Strong experience with OpenAI GPT models and their practical applications.
• Experience with agentic technologies (e.g., Autogen, LangGraph, CrewAI) for multi-agent systems.
• Familiarity with Microsoft Azure Cognitive Services and Azure AI Studio.
• Solid grasp of machine learning fundamentals, including training, fine-tuning, and evaluating language models.
• Practical knowledge of Natural Language Processing (NLP) techniques.