The ad says“Background in NLP, semantic search, or agentic retrieval”
The ad says“Hands-on experience with OpenSearch or Elasticsearch”
The ad says“Experience running embedding inference at large scale”
The ad says“Hands-on ranker model training: feature engineering, pipelines, offline evaluation”
The ad says“Experience building hybrid (lexical + vector) retrieval systems”
The ad says“Sharding, index management, and real-time ingestion at scale”
The ad says“Strong query understanding fundamentals: intent modeling, query expansion”
The ad says“Proven full ML lifecycle ownership: training, deploying, and serving models in production”
The ad says“Background in NLP, semantic search, or agentic retrieval”
The ad says“Hands-on ranker model training: feature engineering, pipelines, offline evaluation”
The ad says“Hands-on experience with OpenSearch or Elasticsearch”
The ad says“Strong query understanding fundamentals: intent modeling, query expansion”
The ad says“Strong query understanding fundamentals: intent modeling, query expansion”
The ad says“Sharding, index management, and real-time ingestion at scale”
The ad says“Background in NLP, semantic search, or agentic retrieval”
The ad says“Sharding, index management, and real-time ingestion at scale”
The ad says“Experience with TypeScript in backend systems”
You’ll own the full ML lifecycle for ranking and retrieval, from training through deployment and production serving. Our search indexes large-scale, user-generated content across a multi-tenant platform where permissions-aware retrieval is critical. You’ll build the systems that decide what surfaces first
Train, deploy, and serve ranking models in production, owning the full ML lifecycle
Build ranker features, training pipelines, and offline evaluation frameworks
Design and scale hybrid retrieval combining lexical and vector search (including HNSW with disk offloading)
Run embedding inference at billions-of-documents scale
Improve query understanding through intent modeling and query expansion
Build permissions-aware retrieval that respects multi-tenant boundaries
Create measurement frameworks to evaluate and improve search quality
Collaborate with Search Infrastructure, AI, and backend teams to integrate ranking improvements across the platform
Benefits
16” MacBook Pro
Moving Expenses
$200/mo commuter benefits
Team lunches each week
401(k) match up to 2%
Unlimited snacks, kombucha, and cold brew
Health insurance
Dental insurance
ClickUp swag
Teammate recognition rewards
Flexible PTO
Preferred experience
Experience building hybrid (lexical + vector) retrieval systems
