SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 500,000 - 0 / annual
OpenArt is an AI storytelling and visual creation platform used by millions of creators worldwide. You'll lead the agentic architecture behind OpenArt's next generation of 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 leadership role, not research. You'll own the end-to-end agent harness architecture, including tool use, context/memory management, multi-step planning, and sub-agent orchestration. You'll design how agents plan and execute long-running creative tasks across multiple model vendors, with clear failure modes and recovery paths.
Key responsibilities:
- Own the complete agent harness architecture powering conversational and autonomous creative workflows
- Design long-horizon planning and execution for creative tasks (scene planning, storyboarding, asset generation, revision loops) across multiple model vendors
- 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, defining patterns other engineers use to add new ones
- Build evaluation and observability stacks with automated evals, regression suites, tracing, and quality gates
- Drive reliability, latency, and cost per successful run as first-class metrics
- Ship polished production frontend experiences (React/Next.js) for agent-driven products end-to-end
- Set technical standards for agent engineering: architecture reviews, engineering standards, and mentorship
- Track the fast-moving agent ecosystem and decide what belongs in OpenArt's stack
- Partner closely with founders, product, design, and GTM to translate user needs into technical direction
You'll work in a founder-led engineering culture where both founders are technical and deeply involved in product and architecture. High ownership, low process — judgment, clarity, and speed are valued over bureaucracy.
REQUIREMENTS:
- 7+ years of full-stack engineering experience shipping and owning production systems at scale, including 2+ years building LLM-powered agents in production (not prototypes or demos)
- Deep, hands-on experience with agent architecture: tool use, context/memory management, multi-step planning, sub-agent orchestration, and long-running workflows
- Track record of designing evaluation frameworks and observability for agentic systems — ability to measure whether an agent is working and prevent regressions
- Strong system design and data modeling skills — comfortable reasoning about state, schemas, and APIs for real product use cases
- Experience authoring reusable Agent Skills, structured agent workflows, or equivalent abstractions that other engineers build on
- Demonstrated technical leadership — you've set direction for a system or team, and people follow your architectural calls because they've been right before
- Strong AI-assisted coding practice — you use tools like Claude Code, Codex, or Cursor as a core part of how you build, with real opinions about what makes them work well
- High product sense — you think about what makes an agent experience feel trustworthy and delightful, not just functional
- Strong communication skills — you can explain agent behavior and technical trade-offs clearly to founders, designers, and non-technical teammates
NICE TO HAVE:
- Practical experience building MCP servers and CLI tooling for agents
- Experience with agent orchestration frameworks (Claude Agent SDK, LangGraph, or similar) and LLM evaluation/observability tooling
- Hands-on experience with image/video generation models and creative asset pipelines
- Experience with guardrails, safety, and cost controls for autonomous systems
- Startup experience or ownership of a product surface from 0 to 1
