Antigravity Performance Lab: Cut LLM Latency & Cost Without Killing Quality

Join us for an exciting new session in the MoonTech series:

Antigravity Performance Lab: Cut LLM Latency & Cost Without Killing Quality

In this talk, Asma Merabet will explore practical strategies to optimize Large Language Model (LLM) performance while maintaining high output quality. As LLM-powered systems become central to modern applications, reducing latency and operational cost without sacrificing reliability is one of the key engineering challenges.

Through real-world insights and technical perspectives, the session will cover approaches to improve model efficiency, streamline inference pipelines, and design smarter AI systems that scale sustainably.

👩‍💻 Speaker: Asma Merabet

PhD Student in Artificial Intelligence, Backend Developer at DeepMinds, and Google Developer Expert in Artificial Intelligence.

📅 Date: 10 March 2026

⏰ Time: 10:00 PM

Don’t miss this opportunity to learn how cutting-edge AI systems can be made faster, more efficient, and production-ready. Join us for a deep dive into the future of optimized AI performance. 🌙🤖

Agenda

---

Speaker

Asma Merabet

Host

Asma Merabet

Complete your event RSVP here: https://gdg.community.dev/events/details/google-gdg-setif-presents-antigravity-performance-lab-cut-llm-latency-amp-cost-without-killing-quality/.