Lead AI Engineer: Agent Architecture & Behavior

Artisan; California (MO); On-site; USD 250,000 - 325,000; Full time

Job summary

Artisan is hiring a hands-on technical lead to design and build the AI architecture for an ambitious new project in San Francisco. You will own agent architecture, multi-agent coordination, and reliable execution, delivering production-grade systems with careful tool choice and scalable memory.

You will work across planning, tool interfaces, evaluation, and experimentation, writing robust code in Python or TypeScript and partnering with engineers and leadership to ship high-impact AI technology.

Qualifications

• Built and shipped a substantial agentic system or production-grade equivalent.
• Deep practical experience with LLM tool use, planning and context engineering.
• Hands-on browser automation in an agentic system, observing state and recovery.
• Excellent software engineering in Python or TypeScript; async services and state machines.
• Ability to distinguish model responsibilities from coded guarantees; handle uncertainties.

Responsibilities

• Design and implement agent architecture and behavior for production use.
• Build multi-agent systems with delegation, coordination, and context sharing.
• Ensure reliable execution with checkpoints and recovery strategies.
• Improve memory, retrieval, and persistent state for agents and skills.
• Create evaluations and experiments; analyze trajectories and failures.
• Make informed model vs tooling decisions; lead key architecture choices.
• Provide technical leadership and align engineering with product goals.

Skills

Agentic system design

LLM tool use

Planning & context engineering

Multi-agent coordination

Browser automation

Asynchronous services

Python

TypeScript

Tools

Python

TypeScript

Job description

Artisan is hiring a hands-on technical lead to design and build the AI architecture for an ambitious new project in San Francisco. You will own agent architecture, multi-agent coordination, and reliable execution, delivering production-grade systems with careful tool choice and scalable memory.

You will work across planning, tool interfaces, evaluation, and experimentation, writing robust code in Python or TypeScript and partnering with engineers and leadership to ship high-impact AI technology.