Senior AI Platform Engineer - Supernal

Location: Remote (Global)Reports to: Head of ProductCompany: SupernalType: EOR FTE or ContractorRate: $50/hrAbout SupernalAt Supernal, we help SMBs hire their first AI employee. Our AI teammates are built with intelligent, agentic workflows and deployed on our proprietary platform. We don't build tools — we deliver working, value-generating AI Employees.Our AI Platform Engineers, known internally as Masons, are the builders behind these systems. Now, we're looking for a Senior Mason to help lead this craft.The RoleAs a Senior AI Platform Engineer, you'll be on the frontlines of our most critical customer implementations, with a strong focus on conversational AI agents deployed in real business environments.You'll design, build, and deliver agentic systems that handle live users, multi-turn conversations, real-time constraints, and complex integrations. These are not demos or experiments — they are production systems that customers rely on.Beyond hands-on engineering, you will act as a technical owner for client delivery. You'll translate customer requirements and SOWs into working systems, own delivery timelines, manage technical tradeoffs, and ensure successful outcomes in production.This is a hands-on role. You're not just reviewing PRs or sitting in meetings — you're in the weeds, building systems, debugging failures, and showing others how it's done.ResponsibilitiesBuild advanced AI agent workflows on n8n and Supernal's proprietary platformDesign, implement, and deploy conversational agents, including multi-turn flows, state management, and tool usageOwn end-to-end technical delivery for high-priority customer implementations, from architecture through production launchTranslate customer requirements and SOWs into clear technical designs, execution plans, and deliverablesMake and own architectural decisions across LLM orchestration, RAG design, API integrations, and workflow decompositionHandle real-world voice system challenges including latency, interruptions, fallbacks, error handling, and failure recoveryWrite automated tests — unit tests for isolated logic and end-to-end tests for full workflow and user journey validationApply solid error handling: distinguish retryable vs. fatal failures, surface meaningful error messages, and avoid silent failuresActively debug complex production issues across agent logic, prompts, integrations, and external dependenciesPartner with delivery and product leadership to manage timelines, scope, and technical tradeoffs during implementationReview technical work for quality, scalability, and maintainability, setting a high bar for engineering excellenceDefine, document, and evolve best practices for building and delivering reliable AI EmployeesYou Might Be a Fit If You...Have 4+ years of experience as a software engineer, automation engineer, or systems builder shipping production systemsHave hands-on experience deploying voice agents using leading platforms (e.g., ElevenLabs, Retell, Nextiva), including telephony and streaming audio integration patternsUnderstand multi-turn conversation designstate management, context windows, interruption handling, and graceful recoveryHave tackled real-time constraints in production: latency budgets, streaming audio, fallback paths, and API chaosWrite automated tests as a matter of course — unit tests, integration tests, and end-to-end workflow validation — and treat testing as part of shipping, not an afterthoughtApply solid engineering fundamentalserror handling, retry strategies, separation of concerns, and clean interfaces between componentsAre comfortable owning delivery outcomes end-to-end — not just writing code — including timelines, reliability, and client successHave deep experience with agentic architectures, workflow automation platforms (n8n, Zapier, Make), and APIsUnderstand LLM orchestration, prompt engineering, function calling, and retrieval-augmented generation (RAG)Can prototype fast and finish the job to production quality — with tests, error handling, monitoring, and runbooksAre an elite debugger who can reason through edge cases, flaky agents, and real-world API failuresCommunicate clearly and fluently in English — both in writing and verbally — especially when articulating technical decisions, tradeoffs, and implementation choices to technical and non-technical stakeholders alikeCan run meetings, drive decisions, write crisp updates, and ask the right questions early — without needing heavy processThrive in fast-paced, ambiguous startup environments and take ownership without being askedBring a low-ego, high-integrity approach to collaboration and leadershipWhat Success Looks LikeVoice-first AI Employees are delivered on time, meet customer requirements, and perform reliably in productionClient implementations are predictable, well-architected, and resilient under real-world conditionsComplex conversational and voice workflows behave consistently and recover gracefully from failureCode is well-tested, well-documented, and maintainable — not just functionalTechnical decisions are communicated clearly and proactively to stakeholders, with tradeoffs explained and risks surfaced earlyEngineering best practices reflect real production learnings and are widely adopted across the Mason teamDelivery artifacts — runbooks, SOPs, reusable components — raise the bar for the whole teamJ-18808-Ljbffr