HackerTrans
TopNewTrendsCommentsPastAskShowJobs

semi_sentient

no profile record

Submissions

The infrastructure behind modern ranking systems (serving, data, MLOps)

shaped.ai
1 points·by semi_sentient·8 mesi fa·2 comments

How Retrieval Works in Modern Ranking Systems

shaped.ai
1 points·by semi_sentient·9 mesi fa·1 comments

How Modern Ranking Systems Work

shaped.ai
3 points·by semi_sentient·9 mesi fa·1 comments

Action Is All You Need: Dual-Flow Generative Ranker 4× Faster and More Accurate

shaped.ai
1 points·by semi_sentient·10 mesi fa·0 comments

comments

semi_sentient
·8 mesi fa·discuss
Follow-up posts for context (same series):

Part 2 – Data Layer (feature store to prevent online/offline skew; vector DB choices and pre- vs post-filtering): https://www.shaped.ai/blog/the-infrastructure-of-modern-rank...

Part 3 – MLOps Backbone (training pipelines, registry, GitOps deployment, monitoring/drift/A-B): https://www.shaped.ai/blog/the-infrastructure-of-modern-rank...

Happy to share more detail (autoscaling policies, index swaps, point-in-time joins, GPU batching) if helpful.
semi_sentient
·8 mesi fa·discuss
Modern ranking systems (feeds, search, recommendations) have strict latency budgets, often under 200 ms at p99. This write-up describes how we designed a production system using a decoupled microservice architecture for serving, a feature + vector store data layer, and an automated MLOps pipeline for training → deployment. This is less about modeling, more about the infrastructure that keeps it all running.
semi_sentient
·9 mesi fa·discuss
Retrieval is the stage where a ranking system narrows billions of items down to a few hundred candidates, fast enough for real-time use. It’s the least visible but most constrained layer: latency budgets, freshness, and recall all collide here.
semi_sentient
·9 mesi fa·discuss
A concise explainer of the standard four-stage architecture used in most modern recommendation and ranking systems: retrieval, scoring, ordering, and feedback.

It walks through how these stages connect in production systems like search, feeds, and content recommendations, with diagrams and examples.

Part of a five-part series exploring each stage in more detail this week.

Curious how others here are evolving these pipelines. Are you moving toward more unified (retrieval+scoring) models, or keeping stages separate for latency and control?
semi_sentient
·10 mesi fa·discuss
shrug maybe the solution on something like this is where every nth post is a personalized one.
semi_sentient
·10 mesi fa·discuss
agreed, but looking at the article it looks like you can turn this personalization bit up or down though to find the mama bear/just right level?