Staff AI Engineer — Permitting Intelligence & Systems

Pulley; San Francisco (CA); Hybrid; USD 300,000 - 350,000; Full time

Benefits offered by this job

Competitive compensation

Meaningful equity

Health & dental insurance

In-person and remote work options

401(k)

Job summary

Pulley is seeking a Staff AI Engineer to lead end-to-end AI product work, shaping the technical direction for LLM applications across multiple surfaces. You will own complex, messy inputs and transform them into fast, structured outputs, with a focus on reliability and production readiness.

Based in the San Francisco Bay Area, you will mentor engineers, define evaluation standards, and drive architecture decisions for agent-driven workflows, aiming to accelerate permitting processes and reduce

Qualifications

• 8+ years of software engineering experience, with a substantial portion building production LLM or ML systems.
• Track record of owning a significant AI domain end-to-end: from problem to production ownership, including data quality, eval design, cost and latency, failure handling.
• Deep hands-on experience with large language models in production—prompting, retrieval-augmented generation, structured extraction, tool use and agentic workflows.

Responsibilities

• Own the AI problem space—define the technical direction for how Pulley applies LLMs across multiple product surfaces, and carry it from ambiguity through architecture to shipped product.
• Turn unstructured permitting documents, city regulations, and jurisdiction workflows into structured, reliable outputs—extraction, classification, retrieval, and agentic workflows.
• Set the evaluation and observability standard for the company: define ground truth, measure quality and regressions, and build the systems that ensure model improvements are adopted.
• Build with AI agents as a daily practice—directing, reviewing, and shipping agent-driven work at high velocity while maintaining quality.
• Make the technical bets for next year—models, architectures, and what to build vs. buy—and own those outcomes in production.
• Multiply engineers by setting patterns, mentoring toward larger scope, and accelerating team speed through systems and standards.

Job description

Pulley is seeking a Staff AI Engineer to lead end-to-end AI product work, shaping the technical direction for LLM applications across multiple surfaces. You will own complex, messy inputs and transform them into fast, structured outputs, with a focus on reliability and production readiness.

Based in the San Francisco Bay Area, you will mentor engineers, define evaluation standards, and drive architecture decisions for agent-driven workflows, aiming to accelerate permitting processes and reduce