Leveraging AI APIs for More Secure, Accurate, and Reliable Applications // MLOps Podcast #252 with Ron Heichman, Machine Learning Engineer at SentinelOne.

// Resume
Effectively integrating AI APIs is critical to building applications that use LLMs, especially given the inherent accuracy, reliability, and security issues that LLMs often exhibit. My goal is to share practical strategies and experiences for using AI APIs in production environments, detailing how these APIs can be adapted to specific use cases, mitigate potential risks, and improve performance. The focus will be on testing, measuring and improving quality for RAG or knowledge workers using AI APIs.

// Biography
Ron Heichman is an AI researcher and engineer dedicated to advancing the field through his work in rapid injection at Preamble, where he helped expose critical vulnerabilities in AI systems. Currently at SentinelOne, he specializes in generative AI, AI alignment, and benchmarking and measuring the performance of AI systems, with an emphasis on Retrieval-Augmented Generation (RAG) and AI guardrails.

// MLOps Jobs board
https://mlops.pallet.xyz/jobs

// MLOps Swag/Merch
https://mlops-community.myshopify.com/

// Related Links
Website: https://www.sentinelone.com/
All the Hard Things with LLMs in Product Development // Phillip Carter // MLOps Podcast #170: https://www.youtube.com/watch?v=DZgXln3v85s&ab_channel=MLOps.community

————— ️Contact us ️ ————-
Join our slack community: https://go.mlops.community/slack
Follow us on Twitter: @mlopscommunity
Register for the next meetup: https://go.mlops.community/register
View all episodes, blogs, newsletters and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/
Connect with Ron on LinkedIn: https://www.linkedin.com/in/heichmanron/

Timestamps:
[00:00] Ron's favorite coffee
[00:20] Takeaways
[01:08] Register now for the Data Engineering for AIML Conference!
[01:59] AI vs ML solutions
[05:42] AI application challenges
[09:38] Evolution of AI models
[19:22] AI tool accessibility challenge
[20:53] Gap in the accessibility of AI tools
[24:00] Optimizing LLM performance
[30:31] Red teaming taxonomy
[36:11] Securing custom LLMs
[44:32] Miscellaneous data in LLMs
[46:29] Automated feedback on data diversity
[50:42] Model stress testing process
[55:49] Benefits of early problem detection
[57:41] Fast injection patterns
[1:02:11] Best jailbreaks seen by Ron
[1:04:53] Data poisoning vulnerabilities
[1:07:48] Wrap up

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.