SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Pulley is an AI-powered platform that accelerates commercial construction and retail expansion by automating permitting intelligence across 19,000+ jurisdictions. The company helps architects, builders, and retailers like J.Crew, Solidcore, and Hibbett Sports eliminate costly delays in project timelines while improving forecasting accuracy.
As a Staff Software Engineer, you will own technical domains spanning multiple product surfaces, driving architectural decisions from ambiguity through shipped, iterated-on product. Your core responsibilities include:
- Define and own technical direction for problem areas, not just individual features. You'll architect solutions that span multiple product surfaces and carry them from initial ambiguity through production ownership.
- Transform unstructured permitting documents, city regulations, and jurisdiction workflows into fast, reliable product experiences, with AI agents as a core component of the product architecture.
- Build with AI agents as a daily practice—directing, reviewing, and shipping agent-driven work at high velocity while maintaining quality standards.
- Make significant technical bets that determine Pulley's product roadmap for the next year, owning the consequences of those decisions in production.
- Multiply team effectiveness by setting technical direction others build within, mentoring senior engineers toward larger scope, and creating systems, standards, and abstractions that make the entire team faster.
You thrive in ambiguity and prefer defining the right problem over executing a spec. You're product-minded and care deeply whether your work solves actual customer problems. You balance strong opinions about quality and velocity without treating them as tradeoffs, instead seeking tools and processes that achieve both. You default to ownership at organizational scale—when something is broken or missing, your instinct is to fix it without needing permission.
Required: 8+ years of software engineering experience with a track record of owning significant technical domains end-to-end. You need fluency in modern full-stack development (TypeScript, React, Google Cloud or equivalent), real production experience building with AI coding agents and LLM-powered features beyond autocomplete, ability to architect durable systems while making pragmatic tradeoffs, and experience mentoring engineers or setting technical direction. You must be based in the San Francisco Bay Area and willing to work in-person 4 days per week.
Nice-to-haves include experience in construction tech, govtech, or proptech; designing evals for LLM-powered features; being the most senior engineer in a domain; or startup experience at the stage where you helped build the team.
