Senior AI Engineer

Pulley (permitting)
San Francisco
Workplace: OnsiteFull timeUSD 230,000 - 280,000 annuallyFunction: Data Science & Machine LearningExperience: 4+ yearsSkills: ["Ownership","Product-minded","Rigor","Mentorship","Problem-solving"]

Build AI-powered permitting intelligence end-to-end, turning messy inputs like scanned plan sets and jurisdiction workflows into reliable structured outputs. Design prompt and pipeline systems, evaluations, and production deployment for LLM/ML features, with strong emphasis on ground truth, quality, observability, and cost/latency. Lead agentic workflows, mentor peers through design reviews, and make technical decisions that directly improve customer delivery timelines.

Loading

Loading job details...

Preparing the role view and application actions.

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

Senior 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 AI-powered permitting intelligence end-to-end, turning messy inputs like scanned plan sets and jurisdiction workflows into reliable structured outputs. Design prompt and pipeline systems, evaluations, and production deployment for LLM/ML features, with strong emphasis on ground truth, quality, observability, and cost/latency. Lead agentic workflows, mentor peers through design reviews, and make technical decisions that directly improve customer delivery timelines.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Own AI-powered features end-to-end, from defining correctness for permitting workflows through prompt/pipeline design, evals, deployment, and iteration.
  • •Convert unstructured permitting documents, city regulations, and jurisdiction workflows into structured outputs using extraction, classification, retrieval, and agentic workflows.
  • •Build evaluation and observability foundations for LLM-powered features, including ground truth, quality/regression measurement, and improvement tracking.
  • •Direct, review, and ship agent-driven work at high velocity while maintaining the quality bar.
  • •Make technical and product decisions with direct customer impact and raise engineering standards through design review and mentorship.

Pay and Benefits

Salary: USD 230,000 - 280,000 annually
Schedule:4-Day Week
Perks:Equity

Key Requirements

  • •4+ years of software engineering experience, with a substantial portion building production LLM or ML systems.
  • •Experience owning an LLM-powered product surface end-to-end (requirements through production), including data quality, eval design, cost/latency, and failure handling.
  • •Deep hands-on experience with large language models in production, including prompting, retrieval-augmented generation, structured extraction, tool use, and agentic workflows.
  • •Experience designing evals and making LLM-powered features reliable in production.
  • •Ability to architect durable systems and work in person 4 days a week while based in the San Francisco Bay Area.
Experience:4+ years
Skills:OwnershipProduct-mindedRigorMentorshipProblem-solving
Tech Stack:LLMMLPromptingRetrieval-augmented generationStructured extractionTool useAgentic workflowsEvalsObservabilityOCRLayout-aware parsingVision-language modelsFine-tuningData pipelinesTypeScriptReactGoogle Cloud

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