SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 300,000 - 0 / annual
OpenArt is an AI storytelling and visual creation platform used by millions of creators worldwide. You'll join a small, founder-led engineering team building the next generation of creative tools powered by cutting-edge AI.
In this role, you'll build the agent layer behind OpenArt's creative products, starting with Director — a tool that lets creators "vibe direct" multi-minute cinematic videos by chatting with AI. This is a product-and-systems role, not research. You'll extend the agent harness (tool use, context management, multi-step planning, evaluation), develop MCP servers and CLI tooling, and ship frontend experiences that make agent capabilities feel effortless.
Key responsibilities:
- Build and extend the agent harness powering conversational and autonomous creative workflows
- Build and maintain MCP servers and CLI-based agent tooling connecting agents to internal services, external model vendors, and creative asset pipelines
- Author reusable Agent Skills and structured workflows for complex, multi-step creative tasks (scene planning, storyboarding, asset generation, revision loops)
- Contribute to evaluation frameworks and observability to catch regressions before users do
- Ship polished, production frontend experiences (React/Next.js) for agent-driven products end to end
- Make pragmatic trade-offs between speed, correctness, and scalability
- Partner closely with product, design, and GTM to translate user needs into technical solutions
- Track the fast-moving agent ecosystem and bring best practices into OpenArt's stack
You'll work closely with founders, the agent team, and design to turn "what should this agent be able to do" into a reliable, scalable system. Engineers own real systems end to end, not slices. Your agents will run for millions of creators, and what you ship shows up in the product within days.
Success in 3–6 months means: shipping a production agent workflow with real users running it, meaningfully improving the harness or eval loop with measurable metrics, owning at least one part of the agent stack end to end, forming tight feedback loops with design and founders, and proactively proposing improvements.
REQUIREMENTS:
- 2+ years of full-stack engineering experience shipping production software
- Hands-on experience building LLM-powered agents or applications that reached real users (not prototypes or demos)
- 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 — you use tools like Claude Code, Codex, or Cursor as a core part of your workflow and have real opinions about what makes them work well
- Product sense — you think about what makes an agent experience feel trustworthy and delightful, not just functional
- Clear communication — you can explain 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 similar) or LLM evaluation/observability tooling
- Hands-on experience with image/video generation models
- Startup experience or having built something 0 to 1 (side projects count)
