Embeddings in Production: Retrieval That Stays Fresh
Keeping vector indexes consistent and low-latency as embeddings and documents change constantly.
San Francisco
Jul 21, 2025 · 2:30 PM
All speakers
Speaker
Lucia Fernandez
Machine Learning Engineer · Forge Data
EmbeddingsVector Search
Lucia builds embedding and retrieval systems at Forge Data, bringing semantic search and recommendations to production with tight latency budgets.
Talks
Vector Search Before It Was Cool
Hard-won lessons building approximate nearest-neighbor systems for recommendations at scale.
Atlanta
Jul 11, 2022 · 10:30 AM