ph3bFounding Engineer: Hands-On, Agent-First /b /h3pbFull-time from day one · Remote worldwide · Competitive salary plus meaningful equity /b /ph3bAbout FrontierU /b /h3pFrontierU is building a private global community for selectively admitted young people aged 16 and over. Members connect with ambitious peers, collaborate, learn, and receive personalised AI mentorship from Socrates. /ppA substantial working platform and automated test suite already exist. We are hiring a hands-on CTO to take full ownership of the technology, complete the product, launch it, and run it. /ph3bThe role /b /h3pThis is not a traditional executive role for someone who has moved away from engineering. /ppYou will personally direct the architecture, development, integration, deployment, security, and operation of FrontierU. You will use AI agents as your primary source of engineering capacity through the agentic harness—or combination of tools—you judge best. /ppNo particular harness is required. You will have the authority to select, combine, replace, or build the tools that produce the best results. /ppYou may build a human engineering team where people add expertise, judgment, or operational coverage. However, FrontierU intends to remain lean. You should know how to get exceptional output from agents before solving every capacity problem through hiring. /ppYou will work directly with the founder and have broad authority over technical execution. You will also be accountable for everything your agents produce. /ph3bYour objectives /b /h3pWithin your first 30 days: achieve full prototype parity. Your first objective is to finish the platform so the implemented product matches FrontierU’s approved product prototype. The prototype, discrepancy analysis, backlog, and acceptance criteria are already documented. Significant parts of the product are already built. /ppYou will: /pulliTake control of the codebase, architecture, backlog, development environments, documentation, and existing agent workflows. /liliTurn the remaining work into clear, independently executable lanes for AI agents. /liliComplete the remaining product experiences, backend behaviour, integrations, and prototype discrepancies. /liliIntegrate and review work that is complete or already in progress. /liliEnsure every feature works end to end. A rendered interface without correct permissions, persistence, error handling, and tests does not count as complete. /liliPreserve FrontierU’s access controls, safeguards for younger Members, audit requirements, and privacy guarantees. /liliKeep the automated tests and all engineering quality gates green. /liliDemonstrate full prototype parity on a production-like staging environment by the end of the month. /liliAny dependency requiring a founder, legal, infrastructure, or vendor decision must be identified during the first week, with a clear recommendation and decision deadline. It must not remain a hidden blocker. /li /ulh3bWithin your first 90 days: launch FrontierU /b /h3pAfter reaching prototype parity, you will make the platform ready for real users and lead its production launch. /ppYou will: /pulliRun structured founder testing, closed-beta testing, and end-to-end testing of all critical journeys. /liliResolve every launch-critical defect and establish a disciplined process for triaging everything else. /liliComplete the production configuration of infrastructure and external services. /liliMaintain the required European data-residency and privacy posture. /liliEstablish monitoring, structured logging, alerts, health checks, operational dashboards, and incident response. /liliPut automated backups in place and prove that production data can be restored. /liliDocument deployment, database migration, rollback, recovery, and security procedures. /liliVerify the security baseline,



including authentication, authorization, rate limiting, secrets, staff permissions, auditability, encryption, and abuse prevention. /liliComplete accessibility testing of public and Applicant-facing journeys and resolve material violations. /liliVerify the platform against agreed performance targets using production-like data. /liliLaunch the platform and remain responsible for its operational stability. /li /ulpYou will: /pulliMaintain the production system and respond quickly when Members or Staff surface bugs. /liliOwn incident response, root-cause analysis, security updates, dependency upgrades, capacity, performance, and infrastructure costs. /liliDefine and meet appropriate reliability and response-time objectives. /liliDeliver the next stages of the product roadmap. /liliImprove FrontierU’s AI systems through evaluations, safety testing, model comparison, and measured iteration. /liliTurn the agent workflow into a durable engineering operating system that others can use. /liliContinuously evaluate new models, harnesses, protocols, and orchestration techniques. /liliAdopt new tools when evidence shows they improve quality, safety, cost, or delivery. /liliAvoid unnecessary dependence on one agent vendor or workflow. /liliHire and lead a small, high-quality human engineering team where justified. /liliMaintain clear technical documentation so the platform is not dependent on one person’s memory. /liliHelp set product priorities and translate them into technically sound delivery plans. /li /ulh3bWhat agent-first engineering means here /b /h3pWe are not looking for someone who occasionally asks an AI assistant to complete a function. We also do not prescribe a particular agentic harness. Selecting and evolving the toolchain is part of your job. You should have strong practical experience setting up and running agents to deliver production software. You should be comfortable with: /pulliComparing agentic harnesses based on quality, control, cost, security, and fit. /liliBreaking large objectives into bounded tasks with explicit acceptance criteria and dependencies. /liliRunning multiple agents across isolated branches, worktrees, sandboxes, or environments without creating integration chaos. /liliAssigning specialised roles for exploration, implementation, testing, security review, and adversarial verification. /liliSelecting appropriate models and reasoning levels for different types of work. /liliCreating reusable skills, instructions, context systems, and domain-specific workflows. /liliConnecting agents to external tools through secure, maintainable interfaces. /liliUsing permissions, persistent context, scheduled automations, and long-running workflows where they improve delivery. /liliManaging context limits, agent handoffs, interrupted work, conflicting changes, and integration dependencies. /liliReviewing actual changes, test evidence, runtime behaviour, and migration safety instead of trusting an agent’s completion report. /liliEstablishing human approval gates around production deployment, data changes, security-sensitive code, and compliance decisions. /liliMeasuring agent quality, cost, latency, failure modes, and throughput. /liliKnowing when parallel execution helps—and when work must remain sequential. /liliReplacing tools when better options emerge without destabilising the engineering process.



/liliBuilding custom orchestration where available harnesses do not meet FrontierU’s needs. /li /ulpYour results matter more than your preferred tooling. We want someone who understands the agent ecosystem deeply enough to make independent technical choices and explain them clearly. /ph3bTechnical foundation /b /h3pFrontierU is a modern full-stack web application backed by a relational database and external services for AI, payments, communications, and file storage. It has extensive automated testing and a continuous integration and delivery process. /ppYou should be comfortable taking ownership of: /pulliModern TypeScript-based web applications /liliComponent-based frontend and server-side development /liliSQL and relational database design /liliSchema changes and production migrations /liliCloud or serverless infrastructure /liliAutomated testing and continuous delivery /liliObservability, backups, recovery, and incident response /liliSecure integrations with external service providers /li /ulh3bWhat we are looking for /b /h3pYou should have: /pulliA record of personally building and operating substantial production web applications. /liliCTO, founding engineer, staff engineer, or equivalent end-to-end technical ownership experience. /liliStrong modern web-development, server-side engineering, SQL, and relational-database expertise. /liliDeep understanding of API design, authentication, authorization, transactions, concurrency, database migrations, queues, idempotency, and failure recovery. /liliProduction experience with cloud infrastructure, CI/CD, object storage, communications, payments, observability, backups, and incident response. /liliExperience building products around language models, including structured outputs, prompt-injection defence, retries, model failures, evaluations, cost control, and safe degradation. /liliAdvanced, demonstrable experience orchestrating AI agents through one or more modern agentic environments. /liliThe ability to assess new agent tools independently rather than following one vendor’s preferred workflow. /liliThe ability to diagnose subtle failures that generated code and ordinary test suites may miss. /liliStrong security and privacy judgment, particularly around GDPR, sensitive data, access control, auditability, and products used by minors. /liliThe ability to communicate technical risks and trade-offs clearly to a non-technical founder. /liliThe judgment to distinguish a genuine blocker from something that can be solved autonomously. /liliThe ability to hire, assess, and lead engineers when a human team becomes necessary. /li /ulpA computer science degree is not required. Evidence of technical depth, ownership, judgment, and shipped work matters more. /ph3bUseful additional experience /b /h3pExperience in any of the following would be valuable: /pulliPrivate communities, social products, marketplaces, education, or talent platforms /liliTrust and safety, moderation, or safeguarding /liliGDPR-sensitive or regulated products /liliAI interviews, assessments, mentoring, or recommendation systems /liliPayment systems and other sensitive third-party integrations /liliAccessibility and performance engineering /liliMulti-agent evaluation, reusable agent skills, tool integrations, or custom orchestration infrastructure /li /ulh3bWhat we offer /b /h3ulliA full-time role from day one /liliRemote work from anywhere, salary premium during the times you stay with us in Florence (digital nomad visa will be arranged) /liliCompetitive salary plus meaningful equity /liliDirect influence over the product, architecture, and company /liliFreedom to choose and evolve the agentic toolchain /liliAuthority to establish the engineering system and selectively build a team /liliThe opportunity to create an unusually capable agent-first technology organisation /li /ul /p #J-18808-Ljbffr

📌 Founding Engineer (Firenze)
🏢 Frontier University
📍 Firenze