Staff AI Engineer: Build the Core AI Assistant & Agent Infra

PermitFlow; New York (NY); Ibrido; USD 180.000 - 240.000; Tempo pieno

Vantaggi offerti da questo lavoro

Competitive salary

Equity

Company-paid health (medical, dental,

401(k)

Unlimited PTO

Home office stipend

Daily in-office meals

Commuter benefits

Descrizione del lavoro

PermitFlow is building a Staff/Principal Engineer role to lead the core AI Assistant, infrastructure, and workflow agents. You will shape the end-to-end agent lifecycle, scale for real construction-use cases, and drive data flywheels that improve over time.

The role requires hands-on engineering leadership, delivering robust agentic systems, and partnering with product and customers to ship high-impact features at scale. Hybrid NYC-based work is offered.

Competenze

• Shipped an assistant or agentic product at meaningful scale.
• Deep knowledge of agentic stack (tool calling, context engineering, memory, orchestration).
• Built eval harnesses that guided team focus and improved trustworthiness of evaluation.
• Strong software engineering in production, owning services.
• Able to influence through code and judgment, not just title.
• 10+ years of software engineering experience with recent focus on LLM-powered products.

Mansioni

• Own the agent architecture: reasoning loop, planning, decomposition, state/session model, recovery for long-running tasks.
• Build the context layer: retrieval, memory, context-window management for documents, requirements, conventions.
• Design the action surface: tools, permissions, human-in-the-loop checkpoints for costly/ irreversible actions.
• Make evaluation the engine of progress: offline/online eval, iterate to improve agent quality based on evidence.
• Set the bar for the org: abstractions, SDKs, review standards for agentic features.
• Stay close to customers: observe permit coordinators, learn from real failures, feed insights back into design.

Descrizione del lavoro

PermitFlow is building a Staff/Principal Engineer role to lead the core AI Assistant, infrastructure, and workflow agents. You will shape the end-to-end agent lifecycle, scale for real construction-use cases, and drive data flywheels that improve over time.

The role requires hands-on engineering leadership, delivering robust agentic systems, and partnering with product and customers to ship high-impact features at scale. Hybrid NYC-based work is offered.