OpenArt is an AI storytelling and visual creation platform used by millions of creators. We are building a new category of AI-native creative tools and are seeking a Senior or Staff Software Engineer to lead the agentic architecture behind our next generation of products, starting with Director, which lets users move a multi-minute cinematic video forward by chatting with AI. You will own the agent infrastructure that enables longer-horizon planning, tool use across multiple model vendors, memory across sessions, sub-agent orchestration, and reliable production operation.

This isn't a research role—it's a product and systems leadership position. You will define the architecture of the agent harness (tool use, context engineering, multi-step planning, orchestration, evaluation), establish engineering standards, and stay hands-on building MCP servers, CLI tooling, and frontend experiences on top of it. You will work closely with the founders and design to translate user needs into technical direction and serve as the technical voice shaping what the agent can do—and how reliably it does it at scale.

What you'll do: - Own end-to-end architecture of the agent harness powering OpenArt's conversational and autonomous workflows: tool use, context/memory management, multi-step planning, and sub-agent orchestration. - Design how agents plan and execute long-running tasks (scene planning, storyboarding, asset generation, revision loops) across multiple model vendors, with clear failure modes and recovery paths. - Build and maintain MCP servers and CLI tooling that connect agents to

OpenArt is an AI storytelling and visual creation platform used by millions of creators. We are building a new category of AI-native creative tools and are seeking a Senior or Staff Software Engineer to lead the agentic architecture behind our next generation of products, starting with Director, which lets users move a multi-minute cinematic video forward by chatting with AI. You will own the agent infrastructure that enables longer-horizon planning, tool use across multiple model vendors, memory across sessions, sub-agent orchestration, and reliable production operation.

This isn't a research role—it's a product and systems leadership position. You will define the architecture of the agent harness (tool use, context engineering, multi-step planning, orchestration, evaluation), establish engineering standards, and stay hands-on building MCP servers, CLI tooling, and frontend experiences on top of it. You will work closely with the founders and design to translate user needs into technical direction and serve as the technical voice shaping what the agent can do—and how reliably it does it at scale.

What you'll do: - Own end-to-end architecture of the agent harness powering OpenArt's conversational and autonomous workflows: tool use, context/memory management, multi-step planning, and sub-agent orchestration. - Design how agents plan and execute long-running tasks (scene planning, storyboarding, asset generation, revision loops) across multiple model vendors, with clear failure modes and recovery paths. - Build and maintain MCP servers and CLI tooling that connect agents to