Senior/Staff Software Engineer, Agent

vibehackers; San Francisco (CA); Hybrid; USD 450,000 - 550,000; Full time

Job summary

OpenArt in San Francisco is seeking a Senior/Staff Software Engineer to lead the agent architecture for our 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.

Join a hands-on leadership role shaping engineering standards, mentoring colleagues, and collaborating with founders, product, design, and GTM to translate

Qualifications

• 7+ years of full-stack engineering shipping production systems at scale.
• 2+ years building LLM-powered agents in production.
• Hands-on agent architecture experience: tool use, memory, planning, orchestration.
• Experience with evaluation frameworks and observability for agentic systems.
• Strong system design, data modeling, and API thinking.
• Proven technical leadership and architectural direction.

Responsibilities

• Own end-to-end agent harness architecture: tooling, orchestration, memory, evals.
• Design long-running planning and execution for creative tasks across models.
• Build MCP servers and CLI tooling connecting agents to services and assets.
• Create reusable Agent Skills and workflows; define extension patterns.
• Develop evaluation and observability stacks with automated evals and gates.
• Drive reliability, latency, and cost-per-run as core metrics.
• Ship production frontend experiences with React/Next.js.
• Set engineering standards and mentor engineers; guide architectural direction.

Skills

Full-stack development

System design

Data modeling

Agent architecture

Observability

Evaluation framework design

Technical leadership

Product thinking

Communication

Mentorship

Reliability engineering

Performance optimization

CLI tooling

Frontend development

Tools

MCP servers

CLI tooling

Claude Agent SDK

LangGraph

LLM tooling

Job description

Uses AI-assisted coding tools (Claude Code, Codex, Cursor) and builds agent-centric tooling; strong connection to vibe coding and AI dev assistants.

About the Role

Lead the design and implementation of OpenArt's agent architecture, owning end-to-end agent infrastructure (harness, orchestration, memory, evals, tooling) to power large-scale creative AI workflows and ship production frontend experiences.

Job Description

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.

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.

Skills

Full-stack development System Design Data Modeling Agent architecture Observability Evaluation framework design Technical leadership Product thinking Communication Mentorship Reliability engineering Performance optimization CLI tooling Frontend development