Software Engineer, Agent
Explicitly builds agent-driven "vibe" experiences and expects AI-assisted coding; works with agent orchestration and model vendors to enable creative workflows.
About the Role
Build and extend the agent infrastructure behind OpenArt's AI-native creative products, enabling multi-step planning, tool use, memory, and reliable production deployment. Ship backend services, CLI tooling, and polished React/Next.js frontends while partnering with product and design to deliver agent-driven workflows used by millions.
Job Description
Role
OpenArt is hiring a Software Engineer to build the agent layer for their creative products. This is a product-and-systems role focused on extending an agent harness, building MCP servers and CLI tooling, and shipping production frontend experiences that make agent-driven creative workflows feel effortless.
Key Responsibilities
- Build and extend the agent harness powering conversational and autonomous creative workflows: tool use, context/memory management, multi-step planning, and sub-agent orchestration.
- Develop and maintain MCP servers and CLI-based tooling that connect agents to internal services, external model vendors, and creative asset pipelines.
- Author reusable Agent Skills and structured workflows to handle complex multi-step creative tasks (scene planning, storyboarding, asset generation, revision loops).
- Contribute to evaluation frameworks and observability to detect regressions and measure agent performance.
- Ship polished production frontend experiences (React/Next.js) end to end for agent-driven products.
- Make pragmatic trade-offs between speed, correctness, and scalability and communicate trade-offs clearly.
- Partner with product, design, and GTM teams to translate user needs into technical solutions.
Requirements
- 2+ years of full-stack engineering experience shipping production software.
- Hands-on experience building LLM-powered agents or agent applications that reached real users (beyond prototypes).
- Working familiarity with agent harness concepts: tool use, context/memory management, multi-step planning, or sub-agent orchestration.
- Solid data modeling and schema design skills for real product use cases.
- Strong AI-assisted coding practice using tools like Claude Code, Codex, or Cursor.
- Product sense for creating trustworthy and delightful agent experiences.
- Clear communication skills for explaining agent behavior and technical trade-offs to non-engineers.
Nice to Have
- Experience authoring reusable Agent Skills or structured agent workflows.
- Practical experience building MCP servers or CLI tooling for agents.
- Exposure to agent orchestration frameworks (Claude Agent SDK, LangGraph) or LLM evaluation/observability tooling.
- Hands-on experience with image/video generation models.
- Startup / 0-to-1 product experience.
Compensation & Work Setup
- Total compensation: $300K - $400K (stated range); $300k+ total compensation also mentioned.
- Equity and meaningful ownership in what you build.
- Bay Area preferred; hybrid available. Visa sponsorship available.
- High autonomy, founder-led engineering culture.
What Success Looks Like in 3–6 Months
- Ship a production agent workflow used by real users inside OpenArt’s ecosystem.
- Improve part of the harness, Agent Skills, or evaluation loop with measurable impact.
- Own a component of the agent stack end to end and be the go-to person for it.
- Establish a tight feedback loop with design, founders, and users and propose proactive improvements.