Senior ML Engineer: Real-Time Ranking & Search in Production

Urban Ridge Supplies; Toronto; On-site; CAD 210,000 - 224,000; Full time

Benefits offered by this job

Competitive equity

Generous PTO

Parental leave

Wellness stipend

Learning & Development

Team offsites

Sabbatical

Job summary

Firecrawl is building ML-powered search and data AI agents. You’ll train and ship ranking and relevance models for our fast-growing product, then extend this work to extraction quality and LLM-driven features. You’ll also own how we measure success with AB testing frameworks and experimentation initiatives.

The Toronto Hub is one of two offices, with on-site work five days a week. This full-time role requires 3+ years of production ML experience and authorization to work in the US or Canada.

Qualifications

• Shipped ML models into production and can own them after launch.
• Real ranking or relevance-modeling experience (learning-to-rank, recommendations, or search quality).
• Experience with large data-heavy systems and pipelines.
• Proficient Python and production-grade backend coding.
• Rigorous about measurement and AB testing.
• Ability to clearly communicate results to the team.

Responsibilities

• Improve ranking and relevance for Firecrawl Search from feature engineering to production.
• Build and tune learning-to-rank models and LLM-driven retrieval.
• Extend ML across products: extraction quality, content classification, and evaluation of features.
• Mine query logs and behavioral data at scale to identify strengths and gaps.
• Create data pipelines turning crawl and query data into training data and features.
• Collaborate with platform, search, and cloud DevOps engineers to run models cheaply in production.
• Design testing strategy with AB testing frameworks and offline evaluation.
• Partner on product launches to define success metrics and decide ship/no-ship.
• Report post-launch performance and drive iterations.

Skills

Shipped ML models in production

Ranking/relevance modeling

Python programming

Data-heavy systems experience

Experimentation & AB testing

Communicating results clearly

Tools

MLflow / MLOps

Kubernetes

Spark

Job description

Firecrawl is building ML-powered search and data AI agents. You’ll train and ship ranking and relevance models for our fast-growing product, then extend this work to extraction quality and LLM-driven features. You’ll also own how we measure success with AB testing frameworks and experimentation initiatives.

The Toronto Hub is one of two offices, with on-site work five days a week. This full-time role requires 3+ years of production ML experience and authorization to work in the US or Canada.