Staff AI Engineer

Pulley (permitting)
San Francisco, Seattle
Workplace: OnsiteFull timeUSD 300,000 - 350,000 annuallyFunction: Data Science & Machine LearningExperience: 8+ yearsSkills: ["Ownership","Product-minded","Rigor","Quality focus","Mentoring"]

Build the AI intelligence behind permitting workflows, turning messy inputs like scanned plan sets, jurisdiction rules, and reviewer comments into structured, trustworthy outputs. Own the technical direction for how Pulley applies LLMs across product surfaces, set eval and observability standards, and ship agent-driven systems with a quality bar. Mentor senior engineers and make durable production architecture decisions using pragmatic tradeoffs.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Pulley (permitting)
Pulley (permitting)
15 hours ago

Staff AI Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 13 hours agoStatus: Live

Job Summary

Build the AI intelligence behind permitting workflows, turning messy inputs like scanned plan sets, jurisdiction rules, and reviewer comments into structured, trustworthy outputs. Own the technical direction for how Pulley applies LLMs across product surfaces, set eval and observability standards, and ship agent-driven systems with a quality bar. Mentor senior engineers and make durable production architecture decisions using pragmatic tradeoffs.
Location: San Francisco, Seattle
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning

Key Responsibilities

  • •Define and own the technical direction for how Pulley applies LLMs across multiple product surfaces, from ambiguity through architecture to shipped iteration.
  • •Convert unstructured permitting documents, regulations, and jurisdiction workflows into structured outputs using extraction, classification, retrieval, and agentic workflows.
  • •Set evaluation and observability standards by defining ground truth, measuring quality and regressions, and building systems for continuous improvement.
  • •Direct, review, and ship agent-driven work at high velocity while owning the quality bar.
  • •Architect durable systems and mentor engineers to create reusable patterns for building LLM features at org scale.

Pay and Benefits

Salary: USD 300,000 - 350,000 annually
Equity and Bonus:Equity
Schedule:4-Day Week
Perks:Equity

Key Requirements

  • •8+ years of software engineering experience, with a substantial portion building production LLM or ML systems.
  • •Own an AI domain end-to-end from problem definition through architecture, delivery, and production ownership (including data quality, eval design, cost/latency, and failure handling).
  • •Hands-on production experience with large language models, including 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 where agents performed substantial implementation under your direction.
Experience:8+ years
Skills:OwnershipProduct-mindedRigorQuality focusMentoring
Tech Stack:LLMsMLPromptingRetrieval-augmented generationStructured extractionAgentic workflowsTypeScriptReactGoogle CloudOCRVision-language models

Company Brief

Pulley (permitting)
Pulley (withpulley.com) provides an AI‑powered permitting platform and expert-backed services to help commercial project teams identify requirements, submit applications, track reviews across 19,000+ jurisdictions, and secure approvals faster.
Industry: Construction Tech
Company Size: Medium (51 to 250 employees)
Growth: Early Stage Startup
Funding: Seed
Headquarters: San Francisco, United States
Founded: 2021
WebsiteLinkedIn