Profile cover
S

AI Embedding Cache Invalidation Engineer

Stella Tran

Full-time · Job · Los_Angeles

About the role

Vector databases cache embeddings to avoid recomputing them on every query. The problem is freshness: when source documents change, their cached embeddings become stale — the vector no longer represents the current content. Queries that should return the updated document keep returning the old one. In a knowledge base that updates daily, stale embeddings silently degrade RAG quality. You'll build the cache invalidation system that keeps vector stores consistent with their source documents. That means detecting which source documents changed since their embeddings were last computed, prioritizing reembedding by document importance and staleness degree, and triggering the reembedding pipeline without disrupting live query serving. The RAG infrastructure team is five engineers. You'll own the invalidation layer — the watchdog that ensures queries always get fresh embeddings — while others handle embedding computation and vector store management.

Responsibilities

  • Build document change detection triggering embedding cache invalidation
  • Prioritize reembedding queue by document importance and staleness
  • Implement zero-downtime invalidation without disrupting live queries
  • Handle different document types: web pages, databases, file systems
  • Monitor cache freshness and alert on staleness threshold violations
  • Optimize invalidation throughput for corpora that update frequently

Requirements

  • 3+ years in backend or infrastructure engineering
  • Understanding of vector databases, embeddings, and RAG architectures
  • Experience with cache invalidation patterns in distributed systems
  • Strong Python and cloud infrastructure skills
  • Systematic approach to consistency problems in distributed systems

Benefits

  • Fully remote with flexible schedule
  • Health, dental, and vision insurance
  • $3,000 annual learning budget
  • Stock options
  • Solve a consistency problem that affects every RAG deployment

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.

Categories

MLOps & AI Infrastructure AI & Machine Learning Engineers

Skills

python docker kubernetes aws sql

Related remote AI jobs

Nearby roles that share similar skills, categories, or hiring intent.

Browse all jobs

Senior Product Security Engineer

RemoteAI company

Full-time Senior

Senior AI R&D Engineer – Model Training (f/m/d)

RemoteAI company

Full-time Senior

AI Resident UK/EMEA

RemoteAI company

Full-time

Devops Engineer, US

RemoteAI company

Full-time

Software Engineer, Infrastructure

RemoteAI company

Full-time

Senior AI Researcher- Pre-training (f/m/d)

RemoteAI company

Full-time Senior

Job Type

Full-time

Level

Mid-Level

Language

English

Salary Range

$100k – $130k / year

AI Expertise

MLOps & AI Infrastructure AI & Machine Learning Engineers

Skills

python docker kubernetes aws sql fastapi

Ready to apply for this role?

Create a free talent account in under 2 minutes.

  • Apply to verified AI companies
  • Get AI-matched job recommendations
  • Message hiring managers directly
  • Build your public AI talent profile
Create free account & apply Log in

Interested in this role? Create your free profile to apply.

Apply — create free profile