Principal Software Engineer, AI

PermitFlow

. Build PermitFlow's core product AI Assistant, infrastructure, and workflow agents .

Posted 10/13/2026full-timeNew York City • New York • United StatesLead💰 $250,000 - $300,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

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

Demonstrates expertise in building AI assistants and agentic products, with a strong focus on software engineering, evaluation harnesses, and context engineering. Proven ability to improve system design through real-world observations and iterative enhancements.

Highest-signal resume keywords

AI Assistant DevelopmentAgentic Product DesignEvaluation Harness CreationSoftware EngineeringLLM-Powered Product Experience

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 EngineeringContext EngineeringMemory ManagementTool DesignOrchestration PatternsTask Completion EvaluationMaintainable Code WritingAgent Reasoning LoopsPlanning and Decomposition StrategiesSession Models

Tools & Technologies

Agentic StackSDKsHuman-in-the-Loop CheckpointsRetrieval SystemsWorkflow Agents

Industry Keywords

PermitFlowProject DocumentsJurisdictional RequirementsCustomer-Specific ConventionsProduction Services

About the role

Key responsibilities & impact

Build PermitFlow's core product AI Assistant, infrastructure, and workflow agents
Design agent reasoning loops, planning and decomposition strategies, state and session models, and recovery behavior for long-running tasks
Build retrieval, memory, and context-window management over project documents, jurisdictional requirements, prior submissions, and customer-specific conventions
Define assistant tools, permissions models, and human-in-the-loop checkpoints
Establish offline and online evaluation harnesses measuring task completion and failure modes
Create iteration loops to improve agent quality based on evidence
Establish abstractions, SDKs, and review standards for agentic features
Work directly with permit coordinators and builders to observe real-world assistant failures and improve system design
Report directly to the VP of Engineering

Requirements

What you’ll need

Experience shipping an assistant or agentic product at meaningful scale
Deep, current knowledge of the agentic stack, including tool calling and tool design, context engineering, memory, retrieval, and orchestration patterns
Experience building evaluation harnesses and understanding trustworthy evaluations
Strong software engineering experience, including owning production services and writing maintainable code
10+ years of software engineering experience
Recent experience building LLM-powered products
Willingness to work 3 in-office days per week in NYC or relocate
Legally authorized to work in the United States

Benefits

Comp & perks

Meaningful equity in a high-growth company
100% company-paid base medical, dental, and vision coverage for employees
Healthcare FSA
401(k) savings plan
Unlimited PTO
Paid family leave
Home office & equipment stipend
Daily in-office lunch and dinner provided
Commuter benefits (pre-tax transit and parking)