Principal Software Engineer, AI

PermitFlow is redefining how America builds. We’re an applied AI company serving the nation’s builders, tackling one of the largest information challenges in the economy: understanding what can be built, where, and how. Our AI agent workforce helps the fastest-growing construction companies navigate everything from permitting and licensing to inspections and project closeouts – accelerating housing, clean-energy, and infrastructure development across the country.

Despite being a $1.6T industry, construction still suffers from massive delays, wasted capital, and lost opportunity. PermitFlow has already delivered unprecedented speed, accuracy, and visibility to over $20B in development, helping contractors reduce compliance time, de-risk projects, and scale with confidence.

As the U.S. enters a new capex supercycle across data centers, factories, housing, and renewables, joining PermitFlow means building the AI infrastructure at the core of every construction project driving the next wave of reindustrialization.

We’ve raised over $90M, most recently completing our Series B, from top-tier investors including Accel, Kleiner Perkins, Initialized, Y Combinator, Felicis, and Altos Ventures, with backing from leaders at OpenAI, Google, Procore, ServiceTitan, Zillow, PlanGrid, and Uber.

We're hiring a Staff/Principal Engineer to build PermitFlow's core product AI Assistant, infrastructure, and workflow agents. This is a role that will require UX and technical acumen to deliver high quality agents in a genuinely complex domain, while also up-leveling our core agentic infrastructure and data flywheel.

Submitting a permit means comprehending construction documents, extracting project details, confirming every requirement has been met and often filling in pdf forms. Errors compound across steps and a failed submission adds real cost for our customers as projects slow.

The ideal candidate will mix an exceptional history of product delivery with true experience building AI and Agentic infrastructure from the ground up. You ship quickly, instrument everything, hold a high quality bar, and stay close to the users of what you build.

This role reports directly to our VP of Engineering. We're hiring at Staff or Principal, with the level based on past experience and interview performance.

• →

  Own the agent architecture. Design the reasoning loop, planning and decomposition strategy, state and session model, and recovery behavior for long-running tasks.

• →

  Build the context layer. Retrieval, memory, and context-window management over project documents, jurisdictional requirements, prior submissions, and customer-specific conventions.

• →

  Design the action surface. Define the tools the assistant can call, the permissions model around them, and the human-in-the-loop checkpoints for actions that are expensive or irreversible.

• →

  Make evaluation the engine of progress. Stand up offline and online eval harnesses that measure task completion and failure modes. Build the iteration loop that lets the whole team improve agent quality on evidence.

• →

  Set the bar for the org. Establish the abstractions, SDKs, and review standards other engineers build agentic features on.

• →

  Stay close to the customer. Sit with permit coordinators and builders, watch the assistant fail in real conditions, and bring that back into the system design.

• You've shipped an assistant or agentic product at meaningful scale

• Deep, current knowledge of the agentic stack (tool calling and tool design, context engineering, memory, retrieval, orchestration patterns, etc)

• You’ve built eval harnesses that changed what a team worked on, and you can articulate what makes an eval trustworthy.

• You are a genuinely strong software engineer, not an AI specialist who needs someone else to make it production-ready. You’ve owned services in production and you write code that other people are glad to inherit.

• You operate with earned authority. You influence through demonstrated judgment, working code, and clear writing rather than title or mandate.

• 10+ years of software engineering experience with recent time spent building LLM-powered products.