Paul SerbanSoftware Engineer
  • PORTFOLIO
  • BLOG

#LangChain

Posts

  • Architecting Production LLM Systems: How AI Gateways, Orchestration, RAG, and Observability Fit TogetherA practical reference architecture connecting OpenRouter, LangChain/LlamaIndex, vector search, structured outputs, and Langfuse into one coherent AI engineering stack

    How AI gateways, LangChain/LlamaIndex orchestration, vector search, structured outputs, and Langfuse observability combine into a production LLM architecture.

    • #AI Engineering
    • #LLM Architecture
    • #Retrieval Augmented Generation
    • #AI Gateway
    • #LangChain
  • Short-Term vs Long-Term Memory in AI Agents: What to Store, When, and WhyA practical engineering guide to memory tiers, retrieval, and forgetting in production agent systems.

    Learn how to design short-term and long-term memory for AI agents, including what to store, retention policies, retrieval strategies, and common pitfalls for real-world deployments.

    • #AI
    • #AI Engineering
    • #AI Agents
    • #Large Language Models
    • #Memory
View all posts
  • LinkedInLinkedIn
  • GitHubGitHub
  • HackerRankHackerRank
  • LeetCodeLeetCode
  • EmailEmail
  • Portfolio
  • My Projects
  • Coursework
  • Blog
  • Posts
  • Snippets
  • Book Notes
  • Cookie Settings
  • Cookie Policy
2026 © Paul Serban. All rights reserved.www.paulserban.eu | Sitemap