About this Event
AI workloads are growing in scale, complexity, and cost. Join us for a hands-on discussion about performance engineering — how to make AI systems faster, leaner, and more efficient.
We’ll cover practical techniques for GPU profiling, bottleneck analysis, and performance tracking using tools like Fixstars AIBooster. You’ll gain insight into:
- How performance engineering improves real-world AI throughput and cost efficiency
- Key bottlenecks in large-scale inference and how to identify them
- Case examples of optimizing GPU, memory, and data pipelines for AI workloads
- Why “hybrid intelligence” — combining human reasoning with performance tools — is central to the future of AI development
After the talk, enjoy free pizza and drinks while connecting with peers driving the next wave of high-performance AI 🍕🍻
You’re welcome to come and go anytime — drop in for the talk, stay for the mixer, or just stop by for a slice and conversation.
Event Venue & Nearby Stays
200 Progress, 200 Progress, Irvine, United States
USD 0.00












