Applied AI Engineer

The role

You will build AI-powered features to turn unstructured permitting documents and city regulations into structured outputs. You will own the end-to-end process from prompt and pipeline design to deployment and evaluation.

What you will do

• Own AI-powered features end-to-end from user interaction to production deployment
• Turn unstructured permitting documents and city regulations into structured outputs
• Build evaluation and observability foundations for LLM-powered features
• Build with AI agents as a daily practice
• Make technical and product decisions impacting customers and projects
• Raise the bar for engineers through design review and mentorship

Required qualifications

• 4+ years of software engineering experience, with a substantial portion building production LLM or ML systems
• Track record of owning an LLM-powered product surface end-to-end
• Deep hands-on experience with large language models in production
• Experience designing evals and making LLM-powered features reliable in production
• Real experience building with AI coding agents
• Ability to architect durable systems while making pragmatic tradeoffs
• Based in the San Francisco Bay Area and willing to work in person 4 days a week

Nice to have

• Experience with document understanding at scale
• Experience fine-tuning models or building data pipelines
• Experience in construction tech, govtech, proptech, or another domain with messy real-world documents
• Experience with modern full-stack development using TypeScript, React, and Google Cloud
• Startup experience at the stage where you helped build the team
• Experience mentoring engineers or leading technical direction across teams

About the company

Pulley helps architects, builders, and retailers speed up projects using AI-powered permitting intelligence. Founded in 2021, the company provides clarity and predictability for commercial projects.