Backend / Automation Engineer (AI Systems) at HYPR | Torre

Backend / Automation Engineer (AI Systems)

Emma highlights
This highlight was written by Emma’s AI. Ask Emma to edit it.
Freelance
Recurrent
Provide your expected compensation while applying
location_on
Remote (specific timezone)
public
GMT-05:00 to GMT-04:00
Shared by
Emma of Torre.ai
25 days ago

Responsibilities


We build production-grade AI automation systems for property-management companies and SMBs.Not demos. Not slideware. Real systems that run unattended in production.Our projects include:AI-powered email triageDocument and invoice processingMulti-system data synchronizationHuman-in-the-loop review appsWorkflow orchestration and automationVoice intake systemsBrowser automation and scraping where APIs don't existWe move fast, ship end-to-end, and care deeply about reliability.Why This Role ExistsWe're growing faster than we can build.We need an engineer who can take a scoped brief, own implementation, and deliver production-ready systems with minimal supervision. You won't be handed isolated tickets or busywork — you'll build systems businesses actually depend on.If you enjoy integrations, debugging ugly APIs, automation reliability, and shipping practical AI systems, this role is for you.What You'll BuildCurrent flagship engagement:A multi-tenant automation platform for a commercial property-management firm that:Syncs Rent Manager and Microsoft 365 data into a local datastoreTriages inbound maintenance emailsDetermines tenant-vs-landlord responsibility using lease dataDetects utility-cost anomaliesGenerates organized audit invoice packages on demandRoutes everything through a human review workflowUpcoming systems include:Twilio + ElevenLabs voice intakePlaywright/Skyvern browser automationAppFolio and Rent Manager write-backsAI-assisted operations toolingWhat You'll OwnBuild scoped client automation systems end-to-endDesign and harden integration pipelinesImplement retries, idempotency, dead-letter handling, and monitoringWork with third-party APIs and undocumented edge casesBuild deterministic guardrails around LLM workflowsWrite tests and validation fixtures for business logicDebug real production issues quickly and pragmaticallyMust-HavesComfortable shipping with:Claude SDKSupabaseVercelGitStrong API integration experience:OAuth/token authPaginationWebhooksRate limitsRetry logicReliability mindset:IdempotencyFailure recoverySilent-failure detectionSolid data modeling instincts:SchemasUpsertsMulti-tenant scopingAble to work from scoped briefs and deliver independentlyComfortable with AI-assisted development workflows (vibe coding) while still understanding and defending your implementation decisionsNice-to-HavesMicrosoft Graph APIPlaywright / browser automationNext.jsPDF/document processingMulti-tenant SaaS experienceProperty-management or fintech domain experienceHow We WorkAsync-first, low-meeting environmentSmall PRs and clean reviewsAI-assisted engineering is normalExplicit scope boundaries and ownershipFast iteration with high accountabilityWe care less about credentials and more about whether you can reliably ship working systems.What Success Looks Like in 90 DaysYou've shipped at least one production client workflow end-to-endYour systems run without babysittingYour PRs are trusted and well-testedYou can take a brief and deliver independentlyCompensation$8–$12/hour initiallyContract role with path to full-timeRate increases as responsibility and ownership growHow to ApplyWe do not screen on resumes.Instead, complete the short proposal exercise below and submit it. Use any AI tools you want — we care that you understand and can defend your decisions.Application Exercise (Required)A US commercial property-management firm uses Rent Manager and Microsoft 365. They want three automations:Triage inbound maintenance emails and determine tenant-vs-landlord responsibilityDetect utility-cost anomalies month-over-monthGenerate organized audit invoice packages on demandYour proposal should cover:Feasibility & technical constraintsArchitecture and core design decisionsData model sketchHow you keep AI outputs trustworthyPhasing and risk managementReliability strategyEstimated effort rangesRequired client access/dependenciesOptional bonus:A small working spike (e.g. Rent Manager API auth + record pull).Clean and thoughtful beats large and unfinished.Strong submissions may lead directly to a paid trial build.