Applied AI Engineer

Pulley

. Own AI-powered features end-to-end, from user conversations and defining correctness through prompt and pipeline design, evaluation, deployment, and production iteration .

Posted 11/6/2026full-timeSan Francisco • California • United StatesMid-LevelSenior💰 $230,000 - $350,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and deploying LLM-powered features, ensuring data quality and reliability through effective evaluation design and system architecture. Capable of mentoring teams and raising engineering standards in AI development.

Highest-signal resume keywords

LLM-Powered Product OwnershipLarge Language Model ExperienceEvaluation Design and ReliabilityDocument Understanding at ScaleTechnical Mentorship

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Software EngineeringProduction LLM SystemsData Quality ManagementStructured ExtractionTool UseAgentic WorkflowsModel Fine-TuningData Pipeline DevelopmentOCRLayout-Aware Parsing

Soft Skills

Technical Decision-MakingMentorshipCollaboration

Tools & Technologies

TypeScriptReactGoogle Cloud

Industry Keywords

Construction TechGovtechProptechAI Coding Agents

Tech Stack

Tools & technologies

CloudReactTypeScript

About the role

Key responsibilities & impact

Own AI-powered features end-to-end, from user conversations and defining correctness through prompt and pipeline design, evaluation, deployment, and production iteration
Convert unstructured permitting documents, city regulations, and jurisdiction workflows into structured outputs through extraction, classification, retrieval, and agentic document workflows
Build evaluation and observability foundations for LLM-powered features, including ground truth, quality measurement, regression tracking, and model-change assessment
Direct, review, and ship AI-agent-driven work while maintaining quality standards
Make technical and product decisions affecting customers and commercial projects
Raise engineering standards for LLM development through design reviews, mentorship, and technical example

Requirements

What you’ll need

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, including data quality, eval design, cost and 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
Experience building with AI coding agents where agents performed substantial implementation under 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
Experience with document understanding at scale, OCR, layout-aware parsing, or vision-language models over scanned PDFs, drawings, or forms (nice to have)
Experience fine-tuning models or building data pipelines for training and evaluation sets (nice to have)
Experience in construction tech, govtech, proptech, or similar domains (nice to have)
Experience with TypeScript, React, and Google Cloud (nice to have)
Startup experience building the team (nice to have)
Experience mentoring engineers or leading technical direction across teams (nice to have)

Benefits

Comp & perks

Equity 📊 Check your resume score for this job Improve your chances of getting an interview by checking your resume score before you apply. Check Resume Score