Gen Ai Development Intern

Summary

Join SonicWall's Gen AI team as an intern and contribute to the development of a next-generation AI chatbot for network device and data monitoring. You will focus on cost optimization by comparing different token extraction techniques to reduce LLM token usage and experimenting with newer LLM models. The internship involves working with Python, AWS Bedrock, and Gitlab. The goal is to reduce LLM tokens and provide a comparison report of different LLM models. This is a remote internship.

Requirements

• Course work in AI and Python programming
• Passion for Gen AI / LLMs
• Cost and performance optimization mindset
• Good attention-to-detail and perseverance in bringing out the best results via experimentation and analysis

Responsibilities

• Compare different static and dynamic extraction techniques to reduce the number of LLM tokens in a given request made to the LLM
• Improvise on the current numbers serving as a baseline for LLM token reduction
• Experiment with additional LLM model(s) to analyze and provide a report on their suitability to the application
• Reduce LLM tokens
• Provide a comparison report of newer LLM model(s) to existing model in terms of accuracy, cost and latency of LLM responses