From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking
05/08/2026 19:20 – Engineering at Meta
Every day, Meta’s recommendation platforms handle billions of user interactions, generating rich temporal signals that capture individual preferences and intent across products, ads, and content.…
GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model
03/08/2026 18:00 – Engineering at Meta
Meta’s Generative Ads Recommendation Model (GEM), the foundation model behind ads recommendations across Instagram and Facebook, now trains at LLM scale on several thousand of…
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
15/07/2026 17:00 – Engineering at Meta
Hierarchical Interest Representation is a research area for Meta Ads. We’re exploring an upstream representation layer over the universe of Ads entities – users, advertisers,…
Modernizing the Meta Ads Service With an Open-Source Kernel Scheduler
13/07/2026 16:00 – Engineering at Meta
TL; DR At Meta’s scale, a few milliseconds of latency degradation can have a significant negative impact on ads performance. When a Linux kernel upgrade…
Meta’s AI Storage Blueprint at Scale
01/07/2026 16:00 – Engineering at Meta
Over the past several years, model capabilities and training dataset sizes have experienced exponential growth. During the past year or so, the time between new-frontier-model…
10 Years of Meta’s Commitment to Python
30/06/2026 16:00 – Engineering at Meta
This year marks Meta’s 10th consecutive year as a sponsor of the Python Software Foundation (PSF), the charitable organization dedicated to advancing, supporting, and protecting…
Privacy-Aware Infrastructure in the AI-Native Era: An Asset Classification Case Study
25/06/2026 22:30 – Engineering at Meta
Privacy controls — systems that enforce retention, access, allowed-purpose, downstream-sharing, or anonymization policies — require a reliable understanding of data to function. Before such…
How Meta Engineered Ultra-Narrow Batteries for AI Glasses
23/06/2026 16:00 – Engineering at Meta
Smart glasses like the Ray-Ban Meta and Oakley Meta Vanguards need to pack enough energy to power features like cameras, speakers, AI workloads, and even…
Adopting AV1 for Real-Time Communication (RTC) at Scale
22/06/2026 16:00 – Engineering at Meta
Adopting AV1 for real-time communication at Meta has been a multi-year effort spanning codec selection, device eligibility, rate control, and error resilience. We’re sharing the…
