Builds evaluation systems to measure Firecrawl's web data extraction quality across diverse websites and workflows. Designs metrics, pipelines, benchmarks, and LLM judges; integrates into CI/CD and model training loops. Requires 3+ years in ML engineering or data quality with production systems.
Builds training infrastructure, reward pipelines, and fine-tuning systems for RL-enhanced LLMs focused on web data extraction. Bridges classical RL and modern LLM agents, ships production models, runs fast experiments. Requires 3+ years in applied RL/ML engineering.
Builds evaluation systems to measure Firecrawl's web data extraction quality across diverse websites and workflows. Designs metrics, pipelines, benchmarks, and LLM judges; integrates into CI/CD and model training loops. Requires 3+ years in ML engineering or data quality with production systems.
Builds training infrastructure, reward pipelines, and fine-tuning systems for RL-enhanced LLMs focused on web data extraction. Bridges classical RL and modern LLM agents, ships production models, runs fast experiments. Requires 3+ years in applied RL/ML engineering.