Software Engineer, Agent

Uses AI-assisted coding tools (Claude Code, Codex, Cursor) and explicitly builds "vibe direct" agent-driven creative workflows. About the Role Build the agent layer and infrastructure for OpenArt's AI-native creative products, implementing agent harnesses, MCP servers, CLI tooling, and polished frontend experiences to enable scalable, reliable agent-driven storytelling and visual creation for millions of users. Job Description Role OpenArt is hiring a Software Engineer to build the agent layer for next-generation creative products. This product-and-systems role focuses on implementing and extending the agent harness (tool use, context/memory management, multi-step planning, sub-agent orchestration), MCP servers and CLI tooling, and frontend experiences to deliver reliable, production-quality agent workflows. Key Responsibilities Build and extend the agent harness that powers 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 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 detect regressions and measure agent performance. 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 closely with product, design, and GTM to translate user needs into technical solutions. Track the agent ecosystem (MCP, Agent Skills, orchestration frameworks) and integrate relevant advances into the stack. Requirements Core Requirements 2+ years of full-stack engineering experience shipping production software. Hands-on experience building LLM-powered agents or applications used by 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 (experience using tools like Claude Code, Codex, or Cursor as core development tools). Product sense for creating trustworthy and delightful agent experiences. Clear communication skills to 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 LLM evaluation/observability tooling. Hands-on experience with image/video generation models. Startup experience or building projects from 0 to 1. Compensation $300,000+ total compensation (base, bonus, equity). Equity and meaningful ownership are included. Work Setup Bay Area preferred (hybrid available). Visa sponsorship available. What Success Looks Like (3-6 months) Ship a production agent workflow used by real users. Improve a part of the harness, agent skills, or eval loop with measurable impact. Own a component of the agent stack end to end and act as the go-to person. Maintain a tight feedback loop with design, founders, and users and proactively propose improvements. Skills Full-stack Development Agent Architecture Data Modeling System Design Frontend Development CLI Tooling Observability Evaluation & Metrics Product Sense Communication Ownership Collaboration AI-assisted Coding Multi-step Planning #J-18808-Ljbffr Vibehackers