Search Engineer, AI Infrastructure — End-to-End Ranking

BlockchainHQ; San Francisco (CA); On-site; USD 235,000 - 260,000; Full time

Benefits offered by this job

Equity

Medical coverage

Dental coverage

Vision coverage

Life insurance

Disability insurance

401(k)

Pre-tax FSA

Commuter benefits

Pet insurance

15+ days PTO

Parental leave

Wellness stipend

Learning budget

Sabbatical (4y)

Team offsites

SF HQ perks

e-bike loan

Job summary

Lavendo is seeking a Search Engineer to own the systems turning the open web into a high-quality, LLМ-driven search index in a fast-moving startup. You will collaborate with the Head of Search and a small team to improve crawling, indexing, retrieval, and serving at scale.

You will own ranking quality end-to-end, ship customer-facing improvements, and optimize latency and cost while maintaining high relevance and reliability.

Qualifications

• 3+ years building production search or retrieval systems
• true
• Must show a measurable impact of a ranking change
• true

Responsibilities

• Own ranking quality and relevance for LLM-driven search and retrieval
• Build and operate the crawling, indexing, retrieval, and search-serving systems behind the product
• Improve search quality using lexical, semantic, hybrid retrieval
• Reduce latency and cost per query at scale while preserving quality
• Own end-to-end production: design, build, deploy, monitor
• Address freshness, deduplication, crawl scheduling at large scale
• Collaborate with Head of Search to shape roadmap and ship improvements quickly

Skills

Production search

Ranking ownership

BM25 lexical

Latency optimization

Go/Python

Lucene/OpenSearch

Kubernetes

AWS/GCP

Protobuf gRPC

Tools

Elasticsearch

OpenSearch

Redis

Kafka

PostgreSQL

Docker

AWS

GCP

gRPC

Protobuf

Job description

Lavendo is seeking a Search Engineer to own the systems turning the open web into a high-quality, LLМ-driven search index in a fast-moving startup. You will collaborate with the Head of Search and a small team to improve crawling, indexing, retrieval, and serving at scale.

You will own ranking quality end-to-end, ship customer-facing improvements, and optimize latency and cost while maintaining high relevance and reliability.