AI Product Engineer

About SunsetAt its core, Sunset was founded to help founders. We started by supporting startups through shutting down, but we have since expanded into unlocking a new revenue stream for all types of <businesses.In> 2025, we had a unique insight: the data every company generates each day through collaboration, communication, and building is some of the most valuable training data in the world. Public and synthetic data can only get frontier models so far, so the next generation of model progress depends on real, proprietary data grounded in how actual businesses operate. We are a primary source of it, partnering directly with the frontier AI labs building what comes next.Why Join Sunset NowWe have scaled from $0 to a multi-eight-figure run rate in a matter of monthsWe have raised from top-tier investors, including Floodgate, Afore, Ludlow, and Hustle FundWe are small enough that you will carry outsized responsibility and grow as quickly as the company doesYou will partner with and build for some of the fastest and most important companies in the worldYou will help build a massive, category-defining business from the ground floorThe RoleThis is a production product-engineering role for someone who has shipped and operated LLM-backed software—not a prompt-engineering, research, or company-wide AI strategy <position.As> our Senior AI Product Engineer, you will turn our early dissolution support agent into a trustworthy product that resolves well-bounded customer needs and establishes the right operating model for more complex workflows. You will move between customer experience, application code, retrieval, tool contracts, model behavior, evaluation, permissions, observability, rollout, and production learning. The goal is correct resolution and customer trust—not maximum deflection or autonomy.What You'll DoOwn AI-assisted dissolution support from the customer problem through production behavior, measurement, and iterationDesign retrieval, context, structured outputs, tool contracts, orchestration, and deterministic boundaries for grounded, inspectable behaviorBuild clear answer, status, no-action, and human-handoff experiences that remain useful when evidence or authority is incompleteCreate representative, versioned evaluations for routing, grounding, usefulness, safety, stability, and real customer outcomesShip with explicit permissions, tenant boundaries, privacy controls, auditability, canaries, rollback, and recoveryInstrument runtime and tool reliability, latency, cost, repeat contact, support effort, and serious failure modesTurn production failures into durable product, evaluation, and system improvementsDetermine whether complex workflows should be automated, AI-assisted, structured for a human, or deliberately remain human-owned, then build the approved product approachSimplify, replace, or remove agentic components when deterministic software or a clearer product experience would work betterWork closely with Product, Support, Security, domain experts, and full-stack engineers who own the surrounding Dissolution productWhat Success Looks LikeCustomers get correct, useful resolution for a meaningful set of dissolution needs—not merely fewer human repliesUnsupported claims and unsafe actions remain inside explicit launch guardrails, with sensitive failures treated as stop-ship issuesHuman handoffs are timely, accurate, and carry enough context to help the customer rather than restart the conversationNew intents move from evidence design through safe release using repeatable evaluation, tool, observability, and rollout infrastructureQuality, runtime reliability, latency, cost, privacy, and customer effort remain visible as the product growsAt least one valuable multi-step workflow has an evidence-backed operating model—automated, AI-assisted, or deliberately human-owned—with clear authority, auditability, and recoveryYou Might Thrive Here IfYou have personally owned a production software product, including an LLM-backed capability beyond a prototypeYou are a strong product engineer who can build across customer experience, application code, backend systems, AI behavior, and production operationsYou understand retrieval, context selection, structured outputs, tool use, orchestration, evaluation, and observability—and know when simpler, deterministic software is the better toolYou can turn ambiguous user needs into explicit evidence, state, authority, and failure boundariesYou have designed for unsupported claims, uncertainty, permissions, privacy, human escalation, rollback, and recoveryYou use representative evidence to make ship, revise, or stop decisions rather than optimizing demos or one aggregate scoreYou enjoy learning a consequential domain and working directly with Product, Support, Security, and engineering partnersYou use modern AI development tools fluently and verify their output with the same rigor you apply to product behaviorThis Role May Not Be for You IfYou want to focus primarily on model research, prompt iteration, or AI infrastructure without owning the complete customer and production outcomeYou believe more autonomy, more model calls, or a more sophisticated agent framework is inherently betterYou prefer to hand off evaluation, security, observability, or production operation after a prototype worksYou want a company-wide AI charter rather than focused ownership of the Dissolution productBonusExperience building customer-support, operations, or multi-step workflow agentsExperience with LangGraph, LangChain, or comparable orchestration approachesExperience with typed tool protocols, retrieval systems, golden datasets, offline evaluation, shadow deployments, or model-based judgesExperience with privacy-sensitive, multi-tenant, audited, legal, financial, or other high-trust productsStrong Python plus TypeScript, React, Node.js, or comparable full-stack experience