LLM Engineer

Responsibilities

• Design and implement chunking and embedding strategies for text and image data
• Develop and optimize prompt engineering techniques for LLM-based systems
• Implement hybrid search and re-ranking mechanisms to improve retrieval accuracy
• Enrich data chunks using metadata filtering and structuring techniques
• Build, test, and validate AI guardrails to ensure safety, quality, and compliance
• Perform AI client testing and evaluation to validate model outputs and performance
• Improve retrieval accuracy and response quality in RAG-based architectures
• Collaborate with AI/ML teams to optimize models and system performance
• Contribute to the design of scalable, high-performance AI retrieval systems

Requirements

• Strong understanding of LLMs, NLP concepts, and RAG architectures
• Skilled in prompt engineering, embeddings, chunking strategies, and hybrid search techniques
• Ability to structure, enrich, and filter data using metadata strategies
• Experience implementing AI guardrails, validation frameworks, and testing methodologies
• Works effectively with cross-functional teams in dynamic environments

About the Company

Capgemini is a global business and technology transformation partner that helps organizations accelerate their transition to a digital and sustainable world. With 340,000 team members in more than 50 countries, Capgemini delivers end-to-end services from strategy and design to engineering, leveraging capabilities in AI, generative AI, cloud, and data.