Staff AI Engineer: Permitting Intelligence Leader

withpulley; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Pulley is seeking a staff-level AI engineer to build the intelligence behind our product, turning messy permitting inputs into fast, structured outputs. You will own the AI direction across surfaces, design robust evals, and push agent-driven workflows at high velocity, mentoring others and shaping tech bets for next year.

Based in the SF Bay Area and willing to work in person 4 days a week, you will influence architecture, data quality, and production readiness for AI features that scale with

Qualifications

• 8+ years of software engineering experience with substantial production ML/LLM systems.
• End-to-end AI domain ownership from problem to production.
• Hands-on production LLM experience: prompting, retrieval-augmented generation, extraction, tool use, agentic workflows.
• Experience designing evals and reliability for LLM-powered features.
• Experience building with AI coding agents, not just autocomplete.
• Ability to architect durable systems with pragmatic tradeoffs.
• Experience mentoring engineers and setting technical direction.
• Based in the San Francisco Bay Area and willing to work in person 4 days a week.

Responsibilities

• Own the AI problem space and define the technical direction across Pulley's product surfaces.
• Turn unstructured permitting documents and regulations into structured outputs—extraction and classification.
• Set evaluation and observability standards and measure model changes over time.
• Build with AI agents and ship agent-driven workflows at high velocity.
• Make technical bets on models, architectures, and builds, and own the outcomes in production.
• Mentor engineers and accelerate the team by defining patterns and abstractions.

Skills

Ambiguity handling

Product minded

Quality and velocity

Ownership at scale

Mentoring engineers

Decision making

Job description

Pulley is seeking a staff-level AI engineer to build the intelligence behind our product, turning messy permitting inputs into fast, structured outputs. You will own the AI direction across surfaces, design robust evals, and push agent-driven workflows at high velocity, mentoring others and shaping tech bets for next year.

Based in the SF Bay Area and willing to work in person 4 days a week, you will influence architecture, data quality, and production readiness for AI features that scale with