AI Explained: Inference, Guardrails, and Observability for LLMs
November 7, 2024
10AM PT / 1PM ET
Registration is now closed. Please check back later for the recording.
The future of Generative AI (GenAI) is bright as it continues to help enterprises enhance their competitive advantage, boost operational efficiency, and reduce costs. However, deploying large language models (LLMs) at scale presents challenges, from handling complex inferences to ensuring AI trust and compliance. Without the right infrastructure, performance bottlenecks, unsafe content, and compliance issues can derail even the most promising AI initiatives.
Watch this AI Explained to learn:
- Strategies for building robust inference pipelines and implementing guardrails for responsible AI, ensuring ethical alignment and compliance
- How to leverage AI Observability to maintain trust and transparency in LLM applications through real-time monitoring and diagnostics
- Insights into optimizing LLM deployments for reliability, maximizing value, and reducing risks from unintended model responses
AI Explained is our AMA series featuring experts on the most pressing issues facing AI and ML teams.
Featured Speakers
Jonathan Cohen
VP of Applied Research
at
NVIDIA
Jonathan Cohen is a VP of Applied Research at NVIDIA, where he is the engineering leader of the Nemo platform. He focuses on incubating new AI technology into products, including NIMs, BioNemo, LLM alignment, speech language models, Nemo guardrails, foundation models for human biology, and genomics analysis. Jonathan spent a total of 14 years at NVIDIA in a variety of engineering and research roles, with a three-year stint at Apple as Director of Engineering in the middle. Earlier in his career, he specialized in computer graphics in the visual effect industry, winning a Scientific and Technical Academy Award in 2007.
Krishna Gade
Founder and CEO
at
Fiddler AI
Krishna Gade is the founder and CEO of Fiddler AI, an enterprise AI Observability startup, which focuses on monitoring, explainability, fairness, and responsible AI governance for predictive and generative models. AI Observability is a vital building block and provides visibility and transparency to the entire enterprise AI application stack. An entrepreneur and engineering leader with strong technical experience in creating scalable platforms and delightful consumer products, Krishna previously held senior engineering leadership roles at Facebook, Pinterest, Twitter, and Microsoft.
