We are seeking a talented Full Stack LLM Engineer to join our team at Accenture. In this role, you will be responsible for developing and deploying end-to-end Large Language Model (LLM) applications that deliver innovative AI solutions to our clients.

Key Responsibilities:

• Design, develop, and deploy full stack LLM applications from concept to production
• Build and optimize RAG (Retrieval Augmented Generation) architectures
• Develop front-end interfaces and back-end APIs for LLM applications
• Implement LLM orchestration frameworks such as LangChain, LlamaIndex, or similar
• Work with cloud platforms (Azure, AWS, or GCP) to deploy and scale LLM solutions
• Collaborate with data scientists, ML engineers, and product teams
• Optimize model performance, latency, and cost
• Ensure security, privacy, and responsible AI practices

Required Skills and Experience:

• Strong programming skills in Python and modern web frameworks
• Experience with LLM frameworks (LangChain, LlamaIndex, etc.)
• Front-end development experience (React, Vue, or Angular)
• Experience with cloud platforms (Azure, AWS, or GCP)
• Knowledge of RAG architectures and vector databases
• Understanding of prompt engineering and LLM fine-tuning
• Experience with containerization (Docker, Kubernetes)
• Strong problem-solving and communication skills