We're the engineers behind Pinterest, building a visual discovery engine powered by the latest in machine learning, billions of ideas and 600+ million users.
San Francisco + beyond
- Tweets 1,278
- Following 36
- Followers 14,420
- Likes 695
Streaming ingestion gives us fresher data in minutes, but how do we know when a partition is complete enough to read?
Learn how we restore that guarantee with Iceberg commits, safe-to-read watermarks and reusable Flink-to-Iceberg sink extensions. medium.com/pinterest-enginee…
2
687
Learn how the team launched the first 3-tower engagement co-train model for ads lightweight ranking at Pinterest, introducing richer user-ad interactions while maintaining the latency and cost efficiency required at scale. medium.com/pinterest-enginee…
1
774
Manas serves billions of embeddings across 80+ clusters at Pinterest, but scaling to tens of billions, we needed new approaches: quantization (50%+ memory savings), SSD-based serving (10x less RAM), & multi-embedding retrieval for richer ranking. Details: medium.com/pinterest-enginee…
6
540
Get to know the story behind building our new multimodal AI foundation with NVIDIA. Our team shares insights about enabling Pinterest Assistant to run 25x more visual context per request. medium.com/pinterest-enginee…
2
526
Today, @Pinterest announced a new foundation for multimodal AI built with @nvidia to support a growing range of products that rely on both images and language.
Learn more: newsroom.pinterest.com/news/…
3
9
6,497
In our latest blog, we introduce Conditional Learned Retrieval, a powerful two-tower architecture combining state-of-the-art ML and modern RecSys methods to balance user engagement with contextual relevance to users' various interests. Learn how we did it: medium.com/pinterest-enginee…
1
7
1,257
🚀We break down RPP - our purpose-built terraform execution engine for securing tens of thousands of AWS resources across hundreds of workspaces.
🔒See how we combine OIDC role-chaining, backend checks, and PR dual controls to lock down multi-repo IaC 👇
medium.com/pinterest-enginee…
1
3
1,038
Calling all aspiring product managers, designers and researchers 📢 Applications for Pinterest’s 2026 Products Apprenticeship Program are now open. Apply now: pinterestcareers.com/departm…
608
Schema changes shouldn't break your offline DB ingestion pipeline.
Our latest blog explores how Pinterest automates schema evolution for its next-generation DB ingestion framework, safely propagating schema changes across Kafka, Flink, Spark, and Iceberg. medium.com/pinterest-enginee…
1
2
696
Adding a second GPU node made training 5x slower.
Our team shares how we moved foundation model training from a broken 0.2x baseline to 7.5x scaling by fixing networking, profiling, communication, and distributed topology.
medium.com/pinterest-enginee…
1
1
12
1,076
Our next Pinterest Labs Talk in one week away! 🚨
UC Berkeley's Dawn Song will join us for a discussion on recent advancements in AI & LLM agents and the risks they present. Register now to attend: pages.beamery.com/Pinterest/…
270
Join us June 25 for our next Pinterest Labs Talk with UC Berkeley's Dawn Song for a discussion on AI & LLM agent advancements and key risks, moderated by Chuck Rosenberg. Register now 👉 pages.beamery.com/Pinterest/…
4
327
Real-time ad retrieval power-up 🚀
Hybrid inference combines sequential transformers + context to blend high-intent signals with long-term user history. Result: 3x–10x Recall@K, ~300% higher median candidate relevance, and measurable ROAS lift. medium.com/pinterest-enginee…
2
5
558
New on the Blog: For large-scale ML systems, moving less data can be just as important as computing faster. This post shares how we reduce unnecessary feature-transfer overhead to improve network efficiency in production.
Read more: medium.com/pinterest-enginee…
1
1
7
748
From Determinantal Point Processes to sliding spectrum decomposition, here's how our team evolved multi-objective optimization at Pinterest to balance what people engage with and what keeps the experience inspiring. medium.com/pinterest-enginee…
1
1
507
At Pinterest, we solved the expensive, manual setup of Android performance metrics by integrating Visually Complete logic into the BaseSurface class.
Our "All-In-One Solution" story 🧵👇
1
1
360
This automatically measures User Perceived Latency on over 60 surfaces, saving two engineer-weeks per feature and encouraging platform-wide performance optimization. Learn more: medium.com/pinterest-enginee…
288
Pinterest Engineering retweeted
Pinterest moved to native CSS carousels to replace legacy JS platform-wide → goo.gle/4cZR6Pk
Using CSS primitives like scroll markers and snap, they achieved:
📉 90% code reduction (2k JS → 200 CSS)
🚀 15% faster page loads
✨ Smoother, interactive UI
25
162
2,095
220,298