Applied AI Engineer

About PermitFlow PermitFlow is building AI agents for the $1.6T construction industry. We’re creating the leading pre-construction platform, starting with the $12B permitting market. Our platform automates the slow, manual permitting process for builders, handling everything from jurisdiction research to application preparation, submission, and real-time tracking. By turning fragmented regulations and workflows into structured, intelligent systems, we help contractors move faster, reduce risk, and scale with confidence. We've raised over $36.5M with Kleiner Perkins leading our Series A, with participation from Initialized Capital, Y Combinator, Felicis Ventures, and Altos Ventures. Our backers include founders and executives from OpenAI, Google, Procore, ServiceTitan, Zillow, PlanGrid, Uber, and more. We are a team of architects, engineers, permitting experts, and product builders who know the pain of pre-construction firsthand and are committed to solving it. Demand is growing faster than we can keep up, and we’re looking for top talent to help us scale. Our HQ is in New York City with a hybrid schedule (3 in-office days per week). We prefer NYC-based candidates or those open to relocation. What You’ll Do As anApplied AI Engineer, you will design and deploy the AI agents that power PermitFlow’s pre-construction platform. You will own the full lifecycle of intelligent agents—from model development to orchestration, productionization, and evaluation—while contributing to core platform engineering. You will: • Develop and deploy AI agents that automate permitting workflows end-to-end • Orchestrate multiple models and tools to create reliable, multi-step AI systems • Build the internal tools and infrastructure that power and monitor these agents • Design and implement backend and frontend services, APIs, and data pipelines, integrating AI functionality into user-facing features when needed • Contribute to system architecture and core platform design with the engineering team • Design and maintain a suite of evaluations and benchmarks to measure agent accuracy, reliability, and cost-effectiveness • Optimize inference pipelines and backend systems for speed, scalability, and cost What We’re Looking For • 3+ years in software or ML engineering post-BS/MS • Hands-on experience shipping production AI/ML systems or AI-powered products • Experience building multi-step ML systems, pipelines, or agentic workflows • Strong backend and API development skills, with some frontend experience • Track record of building reliable products with attention to quality and detail • Startup grit and comfort in fast-moving, evolving environments Benefits • Competitive salary and meaningful equity • 100% paid health, dental, and vision coverage • Company laptop and tools of your choice • Daily meals via UberEats and fully stocked kitchen • Commuter benefits • Team events and offsites • Unlimited PTO Compensation Range: $175K - $265K