Full Stack LLM Developer

We Are:

Accenture is helping companies use generative AI to reinvent their enterprise and optimize business functions for breakthrough innovation and competitive advantage. With over 1,600 professionals dedicated to generative AI, leveraging the depth and experience of more than 40,000 AI and data professionals across the company our Generative AI and LLM Center of Excellence brings together our Experienced Innovation, Strategic Investment, Exceptional Talent, and Power Ecosystem.

You Are:

As a Full Stack Model Developer you will:

• Develop large language model (LLM)-based applications using opensource frameworks like Semantic Kernel, Lang Chain, Llama Index.

• Build, train, and fine tune LLMs to improve performance, accuracy and alignment of the general-purpose models.

• Develop and integrate LLMs and/or LLM applications into products and services. Design, develop, and optimize Artificial Intelligence (AI) prompts.

• Implement AI applications that comply with ethical guidelines and legal standards, particularly regarding data privacy and user consent based on the technical design.

The Work:

• Implement Large Language Models (LLMs) into full-stack applications, ensuring seamless integration and tailoring the capabilities of LLMs to meet specific application needs.

• Create detail design for system components that leverage LLMs or LLM applications.

• Formulate effective prompts for Generative AI models and develop applications using a complete technology stack.

• Apply domain-specific data and techniques for domain adaptation. Enhance model accuracy and effectiveness through fine-tuning.

• Developing solutions for ethical usage of AI and adherence to industry standards and regulations under the guidance of LLM SME and Technical Leads.

• Integrating analytics and monitoring tools to track user interactions, application performance, and the efficiency of LLM integrations.

• Developing and executing comprehensive testing plans for AI applications.

• Collaborate in developing DevOps and MLOps pipelines for application and model deployment.

• Monitor application performance, identify optimization opportunities, and implement solutions to enhance efficiency and scalability.

• Address and resolve technical incidents, troubleshoot both front-end, back-end and LLM integration issues.

• Exploring emerging technologies and their potential integration into business solutions.

• Travel may be required for this role.