SpotOn - Staff AI Engineer

• 5+ years building developer tools, infrastructure, or platform engineering systems - you understand how engineering orgs actually work at scale, not just how AI demos work • 5+ years building developer tools, infrastructure, or platform engineering systems • 2+ years working deeply with LLMs and AI agents in production - not side projects, not hackathons. Production systems handling real code, real reviews, or real task automation. You can speak to failure modes, cost optimization, prompt engineering patterns, and model selection trade-offs from experience. • 2+ years working deeply with LLMs and AI agents in production • Designed and operated AI-assisted code generation or review systems serving 50+ engineers or 30+ repositories. You know the difference between "cool demo" and "trusted by the team." • Designed and operated AI-assisted code generation or review systems • Built multi-agent or agentic workflows - task decomposition, agent specialization, orchestration, error recovery. You've worked with Claude Code, OpenAI Assistants, LangGraph, CrewAI, AutoGen, or custom agent frameworks at a level where you can articulate why you chose one approach over another. • Built multi-agent or agentic workflows • Hands-on with AI coding tools daily - Claude Code, Cursor, GitHub Copilot, Windsurf, Codeium - you don't just use them, you push their limits. You know where they excel and where they hallucinate. You have a personal workflow that makes you measurably faster and you can teach it. • Hands-on with AI coding tools daily • Required domain expertise (at least two of three): • Fintech / payments / regulated industry - you understand what PCI-DSS, SOX, or HIPAA compliance means for code review and deployment. You know why "just let the AI merge it" isn't an option for payment logic. • Fintech / payments / regulated industry • Mobile / Android testing automation - Espresso, UI Automator, or AI-native tools (Drizz, mabl, testRigor). Experience with emulator farms, device provisioning, and CI-integrated test pipelines. • Mobile / Android testing automation • Multi-agent system architecture - you've built systems where multiple AI agents collaborate on decomposed tasks with coordination protocols, fallback strategies, and human-in-the-loop checkpoints. • Multi-agent system architecture • You are not "AI-interested." You are AI-obsessed in the productive sense: • You already write 50%+ of your code with AI assistance and you've measured the impact on your own velocity. You have opinions on which models are best for which tasks and you update those opinions monthly as the landscape shifts. • You already write 50%+ of your code with AI assistance • You've built things with agents that most engineers think aren't possible yet. You're 6-12 months ahead of the mainstream in your personal practice and you have the shipped systems to prove it. • You've built things with agents that most engineers think aren't possible yet. • You prototype in hours, not days. You can go from "I have an idea for how to automate X" to a working POC before end of day. You refine ruthlessly after. • You prototype in hours, not days. • You context-switch across backend, mobile tooling, and AI/ML systems without losing depth. You don't need to be an Android expert, but you need to be dangerous enough to architect the test harness and evaluate the output. • You context-switch across backend, mobile tooling, and AI/ML systems • You communicate technical progress in business terms. You know that "we reduced median PR review time by 47%" lands better with a CTO than "we fine-tuned our prompt chain." You build dashboards, not just systems. • You communicate technical progress in business terms. • You're an evangelist, not a gatekeeper. You get energy from showing other engineers how to work with AI. You don't hoard knowledge - you build systems that make the whole org better. • You're an evangelist, not a gatekeeper. • You have a healthy skepticism forged by real experience. You've seen AI fail in production. You've dealt with hallucinated code, flaky agent workflows, and false-positive reviews. That experience makes your guardrails better, not your enthusiasm less. • You have a healthy skepticism forged by real experience. • What You Won't Be Doing • Building product features for restaurants (that's the rest of the org) • Pure ML/AI research without production deployment • Maintaining legacy systems or writing JIRA tickets all day • People management - you're a pure IC on a small, senior, fast-moving squad. You write more code than anyone on the team. • Tech Environment • Tech Environment • Languages: Kotlin (Android), Go, TypeScript, Python • Languages: • Mobile: Android-native POS applications on dedicated hardware • Mobile: • Infrastructure: AWS, GitHub, CI/CD (GitHub Actions) • Infrastructure: • AI Stack: You'll have significant influence on tool selection - bring your opinions • AI Stack: • Team tooling: Jira, Slack, Figma, standard SpotOn eng stack • Team tooling: • We will never ask candidates to pay fees, purchase equipment, or share sensitive personal or financial information during the hiring process. All legitimate communication from our recruiting team will come from an official company email address (@spoton.com). If something seems suspicious, please contact us at [email protected]. • SpotOn is an equal employment opportunity employer. Qualified candidates are considered for employment without regard to race, religion, gender, gender identity, sexual orientation, national origin, age, military or veteran status, disability, or any other characteristic protected by applicable law. • SpotOn is an E-Verify company.