Senior/Staff Software Engineer, Agent

Role

We are hiring a Senior/Staff Software Engineer to lead the agentic architecture for OpenArt’s next generation of creative products. You will own the full agent harness—tooling, orchestration, memory, evaluation, and reliability—and ship production frontend experiences that enable large-scale, long-running creative workflows.

Key Responsibilities

• Own the end-to-end architecture of the agent harness powering conversational and autonomous creative workflows: tool use, context/memory management, multi-step planning, and sub-agent orchestration.
• Design long-running planning and execution for creative tasks (scene planning, storyboarding, asset generation, revision loops) across multiple model vendors, with clear failure and recovery modes.
• Build and maintain MCP servers and CLI tooling that connect agents to internal services, external model vendors, and creative asset pipelines.
• Author reusable Agent Skills and structured workflows; define patterns for other engineers to extend the system.
• Build evaluation and observability stacks: automated evals, regression suites, tracing, and quality gates.
• Drive reliability, latency, and cost-per-run as core metrics.
• Ship polished production frontend experiences using React/Next.js for agent-driven products.
• Set engineering standards: architecture reviews, mentorship, and technical direction.
• Track the agent ecosystem (MCP, Agent Skills, orchestration frameworks, model capabilities) and decide what to adopt.
• Partner with founders, product, design, and GTM to translate user needs into technical direction and communicate trade-offs.

Requirements

• 7+ years of full-stack engineering experience shipping and owning production systems at scale.
• 2+ years building LLM-powered agents in production (not just prototypes/demos).
• Deep, hands-on experience with agent architecture: tool use, context/memory management, multi-step planning, sub-agent orchestration, and long-running workflows.
• Experience designing evaluation frameworks and observability for agentic systems.
• Strong system design and data modeling skills; comfortable reasoning about state, schemas, and APIs.
• Experience authoring reusable Agent Skills or equivalent abstractions.
• Demonstrated technical leadership and ability to set architectural direction.
• A strong AI-assisted coding practice (experience with Claude Code, Codex, Cursor, or similar).
• High product sense and strong communication skills.

Nice to Have

• Practical experience building MCP servers and CLI tooling for agents.
• Experience with agent orchestration frameworks (Claude Agent SDK, LangGraph) 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.

Compensation

• $500,000+ total compensation (base, bonus, equity).
• Meaningful equity ownership.

Work Setup

• Bay Area preferred; hybrid available.
• Visa sponsorship available.

Success Metrics (3–6 months)

• A clear, documented agent harness architecture adopted by the team.
• A production agent workflow you designed is running for real users.
• Eval and observability loops catch regressions before users see them.
• Measurable improvements in reliability, latency, or cost-per-run on a key workflow.
• Established feedback loop with design, founders, and users; setting direction for agent engineering.