Tool

Kubernetes

25 cases from 20 companies use Kubernetes in their stack. 4 were checked in an online A/B test; 10 report results in production. Tasks: Build a data platform, Evaluate models, Build an assistant over internal docs, Retrieve and rank from millions of items and 10 more. Methods: RAG, Probability calibration, Cross-encoder reranking, BM25, Gradient boosting and 71 more. Companies: X5 Tech, LinkedIn, Avito, Celsus, Target, LY Corporation and 14 more.

Building the AI Retrieval Infrastructure Behind 20 Billion+ Vectors at HubSpotsaas-b2b2026-06
An Authorization Model in a Lakehouse Without Downtimeretail2026-05
ABsalute: A/B Testing Automationretail2026-05
Lemana-GPT: Building a Secure Corporate Gateway to LLMs and Scaling AI Products in Retailretail2026-05
What If Your Page Layout Could Learn? Optimizing with Banditse-commerce2026-05
Building the incremental and online training platform at LinkedInsocial2025-10
Milvus: Building a large-scale vector DB for LINE VOOM's real-time recommendation systemsocial2025-07
How We Created the CV Product and Didn't Burn Outmanufacturing2025-05
Make Retrieval Smarter: How We Built Smart Search over a Document Basegeneral2025-05
AI Sales Agents: Architecture, Bottlenecks and the Evolution of Capabilitiessaas-b2b2025-05
JUDE: LLM-based representation learning for LinkedIn job recommendationsmarketplace2025-05
Machine Learning Service from Scratch, or Creating Frankensteingeneral2024-11
Auto-Generating Product Descriptions in Fashionclassifieds2024-05
Ranking or Calibration? How to Measure the Quality of Advertising CTR Modelsclassifieds2024-05
Monitoring Machine Learning Modelstelecom2024-05
How We Got RAG Running in Productiongeneral2024-05
Incidents in ML Services and How to Monitor Themhealthtech2024-05
How DoorDash Built an Ensemble Learning Model for Time Series Forecastingfood-delivery2023-06
Automating Topic Modeling with AutoTMgeneral2023-05
ML System Design Doc Challenge – Finalbanking2023-05
The Data Infra Behind Zillow's 3x Growth in Experiment Volumemarketplace2023-03
Automatic rule backtesting with large quantities of datamarketplace2022-09
Recommend API: one shared pipeline for many recommendation features at Slacksaas-b2b2022-09
From JSONs to a Data Platformhealthtech2022-06
How We Built Infrastructure to Run User Forecasts at Spotifymedia-streaming2022-06