Skip to main content

Creatify

Software Engineer, Agent

San Francisco Bay AreafulltimemidAdded 3 days ago

About this role

OpenArt is seeking a Software Engineer to build the agent infrastructure powering its next-generation creative products. You'll develop agent harnesses, MCP servers, and frontend experiences that enable creators to direct AI-assisted video and creative workflows at scale.

What you'll do

  • Build and extend the agent harness for tool use, context management, multi-step planning, and sub-agent orchestration
  • Develop MCP servers and CLI tooling connecting agents to internal services, model vendors, and creative asset pipelines
  • Author reusable Agent Skills and structured workflows for complex multi-step creative tasks
  • Create evaluation frameworks and observability systems to monitor agent performance and catch regressions
  • Ship production frontend experiences (React/Next.js) for agent-driven products end-to-end
  • Partner with product, design, and GTM to translate user needs into technical solutions

What they're looking for

  • Full-stack software engineering (2+ years production experience)
  • LLM-powered agent development with real-world deployment
  • Agent harness concepts (tool use, context management, planning, orchestration)
  • Data modeling and schema design
  • AI-assisted coding tools (Claude, Codex, Cursor)
  • React/Next.js frontend development
  • MCP server and CLI tooling development
  • Product thinking and user experience design
Apply with Autofill

Opens the application — the Jobs AI extension fills it for you. Set up autofill

Opens the official application on the employer’s site. No login required.

Creatify

Creatify builds an AI-powered video advertising platform that automates ad creation and distribution for major brands. The company is hiring Full-Stack Engineers, AI Research Engineers, Data Engineers, and Infrastructure/Platform Engineers to develop its SaaS product, data infrastructure, and cloud systems.

View all jobs at Creatify

Likely interview questions

  • Walk us through a production LLM agent you've built—what were the hardest parts about tool use and multi-step planning at scale?
  • How do you approach evaluating agent reliability before shipping to millions of users?
Unlock all 7 questions free — and practice them live →