AI Agent Engineer for Creative Tools

OpenArt AI; San Carlos (CA); Hybrid; USD 320,000 - 420,000; Full time

Benefits offered by this job

Visa sponsorship available

Hybrid work option

Equity ownership

Job summary

OpenArt is building the agent layer behind its next generation of creative products, starting with Director, letting anyone chat with AI to direct multi-minute cinematic videos. You will extend the agent harness for longer-horizon planning, multi-model tool use, and memory across sessions to keep experiences reliable at scale.

This role blends product and system work—extending MCP servers and CLI tooling, shipping frontend experiences (React/Next.js), and collaborating with founders and design

Qualifications

• 2+ years of full-stack engineering experience shipping production software.
• Hands-on experience building LLM-powered agents with real users.
• Familiar with agent harness concepts: tool use, memory management, multi-step planning, or sub-agent orchestration.
• Strong data modeling and schema design skills for real product use cases.
• A strong AI-assisted coding practice using tools like Claude Code, Codex, or Cursor.
• Product sense — you think about agent experience trust and delight, not just functionality.
• Clear communication — you can explain agent behavior and trade-offs to non-engineers.

Responsibilities

• Build and extend the agent harness that powers OpenArt's conversational and autonomous creative workflows: tool use, context/memory management, multi-step planning, and sub-agent orchestration.
• Build and maintain MCP servers and CLI-based agent tooling that connect our agents to internal services, external model vendors, and creative asset pipelines.
• Author reusable Agent Skills and structured workflows for reliable handling of complex tasks: scene planning, storyboarding, asset generation, revision loops.
• Contribute to evaluation frameworks and observability so the team knows when an agent is working well and can catch regressions.
• Ship polished, production frontend experiences (React/Next.js) for agent-driven products, end to end.
• Make pragmatic trade-offs between speed, correctness, and scalability — and communicate them clearly.
• Partner with product, design, and GTM to translate user needs into technical solutions.
• Track the fast-moving agent ecosystem and bring the best into OpenArt's stack.

Skills

Full-stack engineering

LLM-powered agents

Data modeling

AI coding tools

Product sense

Clear communication

Tools

MCP servers

CLI tooling

Agent harness

LangGraph

Job description

OpenArt is building the agent layer behind its next generation of creative products, starting with Director, letting anyone chat with AI to direct multi-minute cinematic videos. You will extend the agent harness for longer-horizon planning, multi-model tool use, and memory across sessions to keep experiences reliable at scale.

This role blends product and system work—extending MCP servers and CLI tooling, shipping frontend experiences (React/Next.js), and collaborating with founders and design