Engineering Manager, AI
$180k - $280k • Remote • New York City, NY • FullTime
Posted 1mo ago
Job Location
New York City, NY
Tech Stack
Remote Work Policy
Fully remote
Employment Type
FullTime
Categories
AI Agent Engineer
About the job
PermitFlow is an applied AI company focused on revolutionizing the construction industry by tackling complex information challenges related to building regulations and project workflows. Our AI agent workforce assists construction companies in navigating permitting, licensing, inspections, and project closeouts, thereby accelerating development. We are building the AI infrastructure that underpins a new era of construction, addressing the industry's historical reliance on fragmented and manual processes. With significant funding and backing from top investors and industry leaders, PermitFlow is at the forefront of automating end-to-end permitting processes using modern AI systems.
Responsibilities
- Lead and grow an engineering team focused on building and hardening agentic infrastructure.
- Foster a strong engineering culture through clear expectations, feedback, and career development.
- Own the technical architecture for workflow agents, including orchestration, model serving, latency, cost, and failure handling.
- Collaborate with Product Management to define and implement systems for release gating based on reliability standards.
- Build and scale evaluation infrastructure, including golden datasets, LLM-as-judge pipelines, human annotation tools, and online monitoring.
- Drive the development of internal tooling for testing, error analysis, and performance improvement of agentic work.
- Enhance system reliability, observability, and engineering efficiency across the AI stack.
- Play a key role in hiring and developing engineers with AI/ML systems expertise and leadership potential.
Requirements
- 5+ years of software engineering experience, with at least 1 year in engineering leadership.
- Direct experience building or shipping a production AI/agentic system, including its surrounding infrastructure.
- Hands-on familiarity with evaluation infrastructure such as golden datasets, LLM-as-judge, human annotation, or online monitoring.
- Strong system design and architecture fundamentals, with the ability to discern appropriate use cases for agents versus simpler systems.
- Ability to navigate ambiguity and translate complex problems into structured execution plans.
- Deep technical fluency, comfortable with code reviews, architecture reviews, and model/system trade-offs.
- Strong communication skills with both technical and non-technical stakeholders, particularly product teams.
- High standards for engineering quality, reliability, and performance.
- Experience in workflow-heavy, enterprise SaaS, or infrastructure products is a plus.
- Exposure to complex regulated environments (e.g., construction, logistics, government) is a bonus.