Staff AI Engineer
Pulley· Engineering
San Francisco$300k - $350kFull-timePosted 4w ago
About the role
Staff-level AI engineer responsible for defining and delivering the AI/LLM-based intelligence across Pulley’s product, converting unstructured permitting inputs into structured outputs, and shaping evaluation, observability, and production-grade AI systems.
Responsibilities
- Own the AI problem space, define the technical direction for applying LLMs across multiple product surfaces, and carry it from ambiguity through architecture to shipped, iterated-on product
- 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
- Set the evaluation and observability standard for the company: define ground truth, measure quality and regressions, and ensure model changes improve the product—build systems that make this the default for every team shipping LLM features
- Build with AI agents as a daily practice—directing, reviewing, and shipping agent-driven work at high velocity while maintaining quality
- Make strategic technical bets for next year (models, architectures, build vs buy) and own production consequences of those bets
- Multiply the engineers around you by setting patterns, mentoring senior engineers, and increasing team velocity through reusable systems, standards, and abstractions
Qualifications
- 8+ years of software engineering experience, with substantial production LLM or ML systems work
- Track record of owning a significant AI domain end-to-end from problem framing to production ownership
- Deep hands-on experience with large language models in production—prompting, retrieval-augmented generation, structured extraction, tool use and agentic workflows
- Experience designing evals and making LLM-powered features reliable in production
- Real experience building with AI coding agents and guiding substantial implementation
- Ability to architect durable systems with pragmatic tradeoffs
- Experience mentoring engineers or setting technical direction for others
- Based in the San Francisco Bay Area and willing to work in person 4 days a week
Skills
Required:Software engineeringLarge language models (LLMs) in productionAI agents / autonomous workflowsEvaluation design and observability for MLSystem architecture for production AILeadership / mentoring
Benefits
- Equity (as part of compensation)
Last updated Sep 24, 2026. Interested? Apply on the company site.
About Pulley
Fast Permitting, Made Simple
Pulley - Construction Permitting Platform
Construction Permitting
More open roles at Pulley
- AI Operations Engineer2w agoHybrid (San Francisco) · Engineering
- Project Manager, Permitting [San Francisco]1mo agoRemote · Permit Operations
- Head of Business Development and Partnerships2mo agoHybrid (New York) · Sales
- Enterprise Account Executive2mo agoHybrid (New York) · Sales
- Head of Legal2mo agoHybrid (New York) · Business Operations