Senior AI Engineer, Permitting Intelligence

withpulley; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Pulley is seeking an experienced Senior AI Engineer in the San Francisco Bay Area to build the intelligence behind our permitting platform. You will own AI-powered features end-to-end, turning messy inputs into fast, structured outputs and shepherding them through prompt design, evals, and production deployment.

You will work with team members to transform unstructured documents and jurisdiction data into reliable outputs, design robust evaluation and observability, and lead with a bias toward

Qualifications

• :

Responsibilities

• Own AI-powered features end-to-end—from talking to users and defining what “correct” means for a permitting workflow, through prompt and pipeline design, evals, deployment, and iteration in production
• Turn unstructured permitting documents, city regulations, and jurisdiction workflows into structured, reliable outputs—extraction, classification, retrieval, and agentic workflows over documents that were never designed to be machine-readable
• Build the evaluation and observability foundation that lets us ship LLM-powered features with confidence: define ground truth, measure quality and regressions, and know when a model change is actually an improvement
• Build with AI agents as a daily practice—directing, reviewing, and shipping agent-driven work at high velocity while owning the quality bar
• Make technical and product decisions that have direct impact on our customers and their projects
• Raise the bar for the engineers around you in how they build with LLMs, through design review, mentorship, and the standards you set in your own work

Skills

ML systems

LLM prompts

RAG

Agentic workflows

Evaluation design

Tools

TypeScript

React

Google Cloud

Job description

Pulley is seeking an experienced Senior AI Engineer in the San Francisco Bay Area to build the intelligence behind our permitting platform. You will own AI-powered features end-to-end, turning messy inputs into fast, structured outputs and shepherding them through prompt design, evals, and production deployment.

You will work with team members to transform unstructured documents and jurisdiction data into reliable outputs, design robust evaluation and observability, and lead with a bias toward