Firecrawl
Search Engineer
About this role
Build the crawling, indexing, and retrieval infrastructure powering Firecrawl's search product. You'll own end-to-end systems that convert web data into LLM-ready formats, optimizing for latency, cost, and scale while working directly with the search leadership team.
What you'll do
- Design and build crawling, indexing, and retrieval systems for Firecrawl Search
- Optimize latency and cost per query as search volume grows
- Improve ranking quality and data freshness for LLM-driven retrieval
- Own services end-to-end from design through production monitoring and iteration
- Collaborate with the Head of Search on product roadmap and priorities
- Handle ambiguous problems independently and ship solutions quickly
What they're looking for
- Backend or distributed systems architecture at scale
- Production infrastructure and operations experience
- Performance optimization (latency, cost, throughput)
- Crawling and indexing technologies
- Search/retrieval systems or information retrieval
- Data ranking and relevance algorithms
- System design and debugging
- Rapid prototyping and iteration
Benefits
- Equity ownership (up to 0.05%)
- 15 days mandatory PTO, unlimited after 24 days
- 12 weeks fully paid parental leave
- $100/month wellness stipend
- $1,000/year professional development budget
- 3 months paid sabbatical after 4 years
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Firecrawl
Firecrawl builds a web data extraction platform that transforms URLs into clean, LLM-ready data for AI applications. The company is hiring Forward Deployed Engineers to embed with customers and drive technical delivery, core platform engineers to own the scrape endpoint and product excellence, search and retrieval specialists to build information systems at scale, and Sales Engineers to help technical buyers adopt the platform.
- Website
- firecrawl.dev
Likely interview questions
- Tell us about a backend or distributed system you've built at scale—what were the biggest performance challenges and how did you solve them?
- How do you approach optimizing systems for multiple competing constraints like latency, cost, and correctness?