Principal Software Engineer, AI

PermitFlow

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

Posted 11/5/2026full-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 agent architecture, including reasoning loops, context engineering, and evaluation harnesses. Proven ability to influence product design and improve agent quality through extensive software engineering experience and LLM-powered product development.

Highest-signal resume keywords

Agent Architecture OwnershipLLM-Powered Product DevelopmentEvaluation Harness BuildingSoftware Engineering SkillsContext Engineering

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

Agentic Stack KnowledgeTool DesignMemory ManagementRetrieval TechniquesOrchestration PatternsTask Completion MeasurementProduction Services OwnershipIteration Loop DevelopmentHuman-In-The-Loop CheckpointsJudgment Demonstration

Soft Skills

Clear WritingInfluencing Skills

Tools & Technologies

SDK DevelopmentContext Layer ManagementAction Surface Design

Industry Keywords

Permit CoordinationAgentic FeaturesReal-World Assistant FailuresNew York City RelocationLegally Authorized to Work in the United States

About the role

Key responsibilities & impact

Own the agent architecture, including reasoning loops, planning and decomposition strategy, state and session model, and recovery behavior for long-running tasks
Build the context layer with retrieval, memory, and context-window management over project documents, jurisdictional requirements, prior submissions, and customer-specific conventions
Design the action surface, including assistant tools, permissions model, and human-in-the-loop checkpoints
Establish offline and online evaluation harnesses measuring task completion and failure modes
Build 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 that changed what a team worked on
Strong software engineering skills and experience owning production services
Ability to influence through demonstrated judgment, working code, and clear writing
10+ years of software engineering experience
Recent experience building LLM-powered products
Willingness to work 3 in-office days per week in New York City or relocate
Legally authorized to work in the United States

Benefits

Comp & perks

Meaningful equity
Bonus
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)