Research Engineer — Search/IR

About the role

You'll own the search and information retrieval systems at the core of Firecrawl — the infrastructure that determines how we find, rank, index, and serve web content at scale. Retrieval quality is Firecrawl's deepest moat. As AI agents increasingly depend on multi-step search and enrichment, the gap between good retrieval and great retrieval compounds. You're the person who closes that gap — and widens it against every competitor.

Responsibilities

• Build and operate search indexes at massive scale.
• Design, build, and maintain the indexing infrastructure that powers Firecrawl's core product.
• Handle billions of documents and care about every millisecond of latency and every byte of storage.
• Own the full stack from ingestion to serving.
• Ingestion, processing, indexing, ranking, query understanding, and serving.
• Solve ranking, relevance, and query understanding.
• Make sure the right content surfaces for the right queries.
• Tackle freshness, dedup, and incremental indexing.
• Run experiments and ship results to production.
• Collaborate closely with the team.

Requirements

• Built search indexes at massive scale.
• Hands-on with ranking, relevance, and query understanding.
• Owns the full stack: ingestion → index → serving.
• Solved freshness, dedup, and incremental indexing problems.
• Self-directed experimenter who ships without handholding.

Qualifications

• Search engineers at companies with large-scale indexes — web search, e-commerce, document search.
• IR researchers who've shipped their work to production.
• Infrastructure engineers who've built and operated real-time indexing pipelines.
• Engineers from Elasticsearch, Algolia, Vespa, or similar search infrastructure teams who got frustrated that they could only tune the knobs and wanted to build the engine.

Skills

• Experience building and operating search infrastructure from scratch.
• Understanding of ranking, relevance, and query understanding.
• Knowledge of BM25, learned ranking, embedding-based retrieval, and when to use which.
• Ability to reason about relevance tradeoffs and ship ranking changes to production.
• Experience with full stack search systems, including ingestion, processing, indexing, ranking, query understanding, and serving.
• Experience with freshness, dedup, and incremental indexing.
• Ability to run experiments and ship results to production.

Benefits

• Generous PTO.
• Parental leave.
• Wellness stipend.
• Learning & Development.
• Team offsites.
• Sabbatical.
• Medical, dental, and vision coverage.
• Life & Disability insurance.
• Pre-tax benefits.
• Pet insurance.

Pay

$180,000–$290,000/year (Range shown is for U.S.-based employees. Compensation outside the U.S. is adjusted fairly based on your country's cost of living. You can explore how we calculate this here: https://www.firecrawl.dev/careers/compensation/)

Schedule

Full-Time