Senior AI Engineer, Pulley

• You thrive in ambiguity—you’d rather define the right problem than execute a spec, and you’re energized rather than paralyzed when the path isn’t laid out
• You’re product-minded: you care whether the thing you built actually solved the customer’s problem, and you’ll talk to users to find out
• You’re rigorous about what “working” means—you don’t trust a demo, you trust an eval, and you build the measurement before you build the feature
• You have strong opinions about quality and velocity and don’t treat them as a tradeoff—you look for the tools, abstractions, and processes that buy both
• You default to ownership: when something is broken or missing, your instinct is to fix it, not to file it as someone else’s problem
• 4+ years of software engineering experience, with a substantial portion building production LLM or ML systems
• Track record of owning an LLM-powered product surface end-to-end: requirements through production, including the unglamorous parts—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, and knowing when each is the wrong tool
• Experience designing evals and otherwise making LLM-powered features reliable in production
• Real experience building with AI coding agents—not just autocomplete; you’ve shipped work where agents did substantial implementation under your direction
• Ability to architect durable systems while making pragmatic tradeoffs
• Based in the San Francisco Bay Area and willing to work in person 4 days a week

Desirable

• In this role, you will build the intelligence behind the product that gets stuff built. Permitting runs on messy inputs—scanned plan sets, jurisdiction code, reviewer comments, application forms that differ in every city—and turning that into something fast, structured, and trustworthy is the core technical problem at Pulley. As a senior-level AI engineer, you will:
• 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