Engineering Manager, AI

permitflow; United States; On-site; USD 180,000 - 240,000; Full time

Job summary

PermitFlow is redefining how America builds. We are seeking an Engineering Manager, AI to lead and scale the engineering team building PermitFlow's core agentic infrastructure and evaluation systems.

This builder-leader role owns both people leadership and technical execution for systems that decide whether an AI agent can submit a permit on its own, or needs a human in the loop. You will report to the VP of Engineering and collaborate with our Product Manager, AI to move the quality bar forward.

Qualifications

• 5+ years in software engineering and 1+ year in leadership.
• Direct experience building or shipping a production AI/agentic system.
• Hands-on familiarity with evaluation infrastructure (golden data sets, LLM-as-judge, human annotation, monitoring).
• Strong system design and architecture fundamentals with judgment on when an agent is ready to submit.

Responsibilities

• Lead and grow an engineering team building and hardening PermitFlow's agentic infrastructure, raising ownership, quality, and execution speed.
• Build a strong engineering culture through clear expectations, 1:1s, feedback loops, and career development.
• Own the technical architecture behind workflow agents: orchestration, model serving, latency, cost per task, and failure handling at scale.
• Partner with Product Manager, AI to define reliability criteria and build systems that gate releases against that bar.
• Build and scale evaluation infrastructure: golden data sets, LLM-as-judge pipelines, annotation tooling, and drift/regression monitoring.
• Drive internal tooling used to test, error-analyze, and hill-climb agentic work across teams.
• Improve system reliability, observability, and engineering efficiency as usage scales.
• Play a key role in hiring and developing engineers with ML/AI systems depth.

Skills

Software engineering

Engineering leadership

AI systems

Evaluation infrastructure

System design

Job description

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.

Building the AI Infrastructure for Construction

Construction remains one of the largest real-world systems still operating on fragmented, manual infrastructure.

Every project in the U.S. moves through permitting and pre-construction workflows spread across ~20,000 jurisdictions - each with inconsistent rules, systems, and levels of digitization.

This creates one of the largest bottlenecks in the physical economy, delaying housing and infrastructure projects and costing billions in lost time and capital every year.

PermitFlow is rebuilding this layer from the ground up - using modern software and AI systems to automate permitting end-to-end.

Our AI agent workforce is the core of that system: it reads construction documents, extracts project details, and drives permits and inspections toward submission with as little human intervention as the accuracy bar allows.

We are still early, and the systems that decide how much of this we can automate are actively being defined.

Role Overview

We're looking for an Engineering Manager, AI to lead and scale the engineering team building PermitFlow's core agentic infrastructure and evaluation systems.

This is a builder-leader role. You will own both people leadership and technical execution for the systems that decide whether an AI agent can submit a permit on its own, or needs a human in the loop.

You will report directly to our VP of Engineering and partner closely with our Product Manager, AI on where the quality bar sits today and what it takes to move it. Our VP strongly values hands-on technical leadership. The best-fit EMs here are deeply technical, comfortable in the weeds of model behavior and eval design, and just as comfortable running a team.

You will be expected to drive your own roadmap end-to-end from technical direction and execution planning through delivery and measurable accuracy and reliability gains in production, not just shipping features but moving the automation ceiling.

What You'll Do

You will operate across systems, people, and execution at scale:

• Lead and grow an engineering team building and hardening PermitFlow's agentic infrastructure, raising the bar for ownership, quality, and execution speed
• Build strong engineering culture through clear expectations, 1:1s, feedback loops, and career development
• Own the technical architecture behind our workflow agents: orchestration, model serving, latency, cost per task, and failure handling at scale
• Partner with our Product Manager, AI to define what "reliable enough to submit" means, and build the engineering systems that gate release against that bar
• Build and scale our evaluation infrastructure: golden data sets, LLM-as-judge pipelines, human annotation tooling, and online monitoring for drift and regression
• Drive the internal tooling every team at PermitFlow uses to test, error-analyze, and hill-climb agentic work
• Improve system reliability, observability, and engineering efficiency across our AI stack as usage and jurisdiction coverage scale
• Play a key role in hiring and developing engineers with genuine ML/AI systems depth, and future leaders on the team

What We're Looking For

We're looking for strong technical leaders who thrive in high-ownership, high-ambiguity environments.

• 5+ years in software engineering, including 1+ year in engineering leadership
• Direct experience building or shipping a production AI/agentic system, not just consuming an API but owning the infrastructure around it
• Hands-on familiarity with evaluation infrastructure: golden data sets, LLM-as-judge, human annotation, or online monitoring
• Strong system design and architecture fundamentals, with judgment on when an agent is the r