Senior/Staff Software Engineer, Agent

Vibehackers; San Carlos, Northern (CA, KY); Hybrid; USD 500,000 - 600,000; Full time

Benefits offered by this job

Equity ownership

Hybrid work

Job summary

OpenArt, in the Bay Area, seeks a Senior/Staff Software Engineer to lead the agent harness architecture behind its next-generation creative products. You will own end-to-end agent planning, tool use, memory management, and production systems that expose capabilities to millions of creators.

You will mentor engineers, set engineering standards, and collaborate with product and design to translate user needs into scalable agent infrastructure and tooling.

Qualifications

• 7+ years of full-stack engineering experience shipping and owning production systems at scale.
• 2+ years building LLM-powered agents in production.

Responsibilities

• Own the architecture and implementation of the agent harness powering conversational and autonomous creative workflows.
• Design long-horizon planning and execution for creative tasks across multiple model vendors.
• Build and maintain servers and CLI-based tooling to connect agents to internal services and external vendors.
• Author reusable Agent Skills and structured workflows; define patterns and standards.
• Build evaluation and observability: evals, tracing, and quality gates.
• Ship polished production frontend experiences end-to-end (React/Next.js).
• Set technical standards via architecture reviews and mentorship.

Skills

Agent architecture

Full-stack development

LLM-powered agents

System design

Observability

Frontend development

Mentorship

Performance optimization

Tooling

Memory/context management

Tools

MCP servers

CLI tooling

LangGraph

Claude Agent SDK

External model vendors

Job description

Uses AI-assisted coding tools like Claude Code, Codex, and Cursor and focuses on building agent-driven, vibe-style creative experiences.

About the Role

Lead the architecture and implementation of OpenArt's agent layer to power large-scale, creative AI workflows. Own end-to-end agent infrastructure (harness, orchestration, memory, evals, tooling) and ship production frontend and tooling while setting engineering standards and mentoring the team.

Job Description

Role

OpenArt is hiring a Senior/Staff Software Engineer to lead the agentic architecture behind their next-generation creative products. You will own the end-to-end agent harness — planning, tool use, memory/context management, orchestration, evaluation, and the production systems and frontends that expose these capabilities to millions of creators.

Key Responsibilities

• Own the architecture and implementation of the agent harness powering conversational and autonomous creative workflows (tool use, context/memory, multi-step planning, sub-agent orchestration).
• Design long-horizon 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-based agent tooling to connect agents to internal services, external model vendors, and creative asset pipelines.
• Author reusable Agent Skills and structured workflows; define patterns and standards other engineers follow.
• Build evaluation and observability: automated evals, regression suites, tracing, and quality gates to detect regressions before users see them.
• Drive reliability, latency, and cost-per-successful-run as first-class metrics.
• Ship polished, production frontend experiences end-to-end (React/Next.js) for agent-driven products.
• Set technical standards via architecture reviews, engineering standards, and mentorship.
• Track the agent ecosystem (MCP, Agent Skills, orchestration frameworks, model capabilities) and decide what belongs in OpenArt’s stack.
• 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, including 2+ years building LLM-powered agents in production (not just prototypes).
• Deep, hands-on experience with agent architecture: tool use, context/memory management, multi-step planning, sub-agent orchestration, and long-running workflows.
• Track record designing evaluation frameworks and observability for agentic systems.
• Strong system design and data modeling skills; comfortable with state, schemas, and APIs for real product use cases.
• Experience authoring reusable Agent Skills, structured agent workflows, or equivalent abstractions.
• Demonstrated technical leadership setting direction for systems or teams.
• A strong AI-assisted coding practice (uses tools like Claude Code, Codex, or Cursor and has opinions on them).
• High product sense and strong communication skills to explain agent behavior and trade-offs to technical and non-technical stakeholders.

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.

Compensation & Work Setup

• Compensation range: $500,000 - $600,000 total compensation (includes base, bonus, equity).
• Equity: meaningful ownership in what you build.
• Work setup: Bay Area preferred, hybrid available. Visa sponsorship available.

What Success Looks Like in 3–6 Months

• A clear, documented architecture for the agent harness that the team builds against.
• A production agent workflow you designed is shipped and running for real users.
• An eval and observability loop that catches regressions before users see them.
• Measurable improvement in reliability, latency, or cost-per-successful-run on an important workflow.
• Tight feedback loop established with design, founders, and users; setting direction for agent engineering.

Skills

System Design Data Modeling Agent Architecture Observability Evaluation Frameworks Reliability Engineering Latency and Cost Optimization Full-stack Development Frontend Development Technical Leadership Mentorship Communication Product Sense AI-assisted Coding CLI Tooling Orchestration Memory/Context Management Workflow and Planning Design Testing and Regression Suites