Deloitte's Assurance practice offers more than just financial oversight. It's about validating achievements, addressing challenges, and building robust foundations for future success. We empower you to anticipate and navigate change effectively.

This role involves designing, developing, and deploying advanced Generative AI solutions, with a strong focus on Large Language Models (LLMs). You will be instrumental in creating and optimizing enterprise-grade AI applications.

Key responsibilities include developing and optimizing Retrieval-Augmented Generation (RAG) pipelines, building and managing embedding-based search systems using vector databases, and crafting, testing, and refining prompts to enhance model performance.

Further, you will integrate and orchestrate LLMs through APIs and AI frameworks for production environments. Collaboration with diverse teams to identify innovative AI solutions and ensuring the scalability, reliability, and performance of GenAI applications are also crucial aspects of this role.

Candidates should possess a B.Sc or B.Tech degree in Artificial Intelligence, Data Science, or a related discipline, coupled with 8-12 years of relevant experience.

Proficiency is required in GenAI frameworks like LangChain or LlamaIndex, cloud AI platforms such as Azure OpenAI or AWS Bedrock, and RAG architectures. A strong understanding of embeddings, vector stores, semantic search, and prompt engineering for LLMs is essential. Experience with various LLMs (GPT, Claude, Gemini, Llama, Mistral) and their integration, configuration, and deployment is necessary. Familiarity with AI-assisted coding tools like GitHub Copilot and knowledge of data privacy, security, and cost optimization techniques for LLMs are also key requirements.