> Markdown version of [/jobs/ext/4620703-search-engineer-ai-infrastructure-sf-toronto](https://www.wearedevelopers.com/jobs/ext/4620703-search-engineer-ai-infrastructure-sf-toronto). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Search Engineer, AI Infrastructure (SF/Toronto)

- **Company:** LAVENDO INC.
- **Location:** San Francisco, CA, United States
- **Experience:** Experienced
- **Contract:** Permanent contract
- **Skills:** Automated Storage and Retrieval Systems, Data Deduplication, Information Retrieval, Python (Programming Language), System Programming, AI Infrastructure, Normalized Discounted Cumulative Gain, Retrieval-Augmented Generation, Large Language Models, Indexer, Backend, Build Management, Low Latency, Search Engines
- **Published:** November 7, 2026
- **Apply:** https://www.juju.com/job/28_25197_f4684b8333ae79ececf9be1178de0544

## About the Role

* 3+ years of experience building and operating search or retrieval systems in production, with ranking and relevance as your primary, owned discipline
 * A specific example of a ranking or re-ranking change you personally owned, the search-quality or business metric it moved, and the numerical impact achieved
 * Hands-on information-retrieval depth across BM25 and lexical retrieval, semantic/vector retrieval, hybrid retrieval, re-ranking, retrieval evaluation, or RAG evaluation
 * Experience measuring search quality through relevance, recall, conversion, CTR, NDCG, MRR, query satisfaction, or comparable production metrics
 * End-to-end ownership of search services: you have designed, shipped, monitored, debugged, measured, and iterated on production systems
 * Strong backend systems programming skills in Go, Rust, Python, or a comparable language.
 * Experience balancing relevance, latency, cost, correctness, and reliability under real production constraints
 * Comfort working through ambiguity, setting technical direction, and shipping quickly with a build-measure-iterate operating style

## Description

As a Search Engine, you will own ranking quality and relevance for an LLM-driven search and retrieval product.

This is a role for an engineer whose primary, hands-on discipline is production search quality. You have personally shipped ranking or re-ranking changes, measured their impact, and can clearly describe the relevance, recall, conversion, or other search-quality metric you improved-including the result.

You will work directly with the Head of Search and a small team across crawling, indexing, retrieval, and search serving. These systems are central to delivering excellent results at scale, but they are not substitutes for relevance ownership. Your role is to improve search quality while navigating the real constraints of web-scale retrieval: freshness, deduplication, latency, reliability, and cost per query.

What You'll Do

 * Own ranking quality and relevance for LLM-driven retrieval
 * Design and build the crawling, indexing, and retrieval systems
 * Push down latency and cost per query while search volume grows
 * Own services end to end: design, ship, monitor, and iterate in production
 * Work directly with the Head of Search and the rest of the search team on the roadmap