Self-Paced Courses

Description 

The Gen AI Lab Onboarding Program is designed to equip new hires with the technical skills and practical experience to effectively build, deploy, and manage Generative AI solutions using large language models (LLMs) and cloud infrastructure. The program spans four weeks and focuses on key areas such as LLMs, prompt engineering, Retrieval-Augmented Generation (RAG) systems, agent-based AI systems, cloud Gan AI services, and MLOps for Generative AI.

 Each week is structured to cover specific areas with hands-on projects, guided learning sessions, and technical deep dives. By the end of the program, participants will be able to independently build, evaluate, and deploy scalable Gen AI solutions.

Program Outcomes

By the end of the four-week onboarding program, participants will have: 

• A deep understanding of LLMs and how to use them effectively in real-world applications
• Mastery in crafting and optimizing prompts to extract the best performance from LLMs
• The ability to build, deploy, and evaluate RAG systems integrating retrieval mechanisms for enhanced AI functionality
• Hands-on experience developing scalable Gen AI applications using LangChain and cloud AI services
• Knowledge of building autonomous LLM agents for complex tasks and decision-making
• The capability to evaluate, monitor, and continuously improve LLM systems in production environments using MLOps principles