Tech Reading and Notes
  • Posts
  • Tag Index
  • Search
  • About
Navigation bar avatar

Posts

Netflix LLM Serving: Triton, vLLM, and Production Tradeoffs

Posted on November 16, 2026

Tags: AI LLM Infrastructure Netflix

Event-Driven Design under a Read-Your-Writes Deadline

Posted on November 9, 2026

Tags: Distributed Systems Kafka Architecture Performance

Netflix Camera Processing and Reproducible Media Jobs

Posted on October 22, 2026

Tags: Netflix Infrastructure Data Engineering

Hybrid Retrieval and the Precision of Exact Identifiers

Posted on October 7, 2026

Tags: AI RAG Search

Netflix Data Deletion as a Distributed Control Plane

Posted on September 9, 2026

Tags: Netflix Data Engineering Distributed Systems

Sharing GPU Pools without Losing Interactive Latency

Posted on August 12, 2026

Tags: AI GPU Infrastructure Performance

Uber Payment Batching and Hot Account Serialization

Posted on July 16, 2026

Tags: Uber Distributed Systems Payments

LinkedIn Hiring Integrations and the Canonical Data Contract

Posted on June 25, 2026

Tags: LinkedIn Data Engineering Architecture

GitHub Agentic Workflows and Staged Writes

Posted on June 12, 2026

Tags: AI GitHub Security CI/CD

Hierarchical RAG across SQL and Documents

Posted on May 27, 2026

Tags: AI RAG Agents Data Engineering

Context-Aware RAG Needs More than a Larger Prompt

Posted on May 12, 2026

Tags: AI RAG Architecture

Pinterest MCP and the Platform around the Protocol

Posted on April 28, 2026

Tags: AI MCP Pinterest Infrastructure

Pinterest Spark Memory Retries and the Cost of Tail Tasks

Posted on April 14, 2026

Tags: Spark Pinterest Data Engineering

AI Incident Triage Needs an Evidence Trail

Posted on March 18, 2026

Tags: AI Observability SRE

Rate Limiting as a Control Plane and an Access Policy

Posted on February 24, 2026

Tags: Infrastructure Uber Distributed Systems
  • Older Posts →
  • Email me
  • GitHub
  • LinkedIn
  • Google Scholar

Xin Ren  •  2026

Copyright © 2025 Xin Ren