{"data":{"id":216564,"slug":"senior-full-stack-engineer","type":"job","title":"Senior Full-Stack Engineer","description":"About agentmama\nWe build AI agents that audit and optimize e-commerce advertising. Our platform syncs live data from Google Ads, Meta, Merchant Center, and Google Analytics, runs it through a rule engine, LLM-powered audit agents, and our own prediction models, and turns the findings into concrete actions marketers can apply with one click.\nWe're a small team shipping fast on a modern, strictly-typed stack. You'd be one of a handful of engineers reporting directly to the CTO, which means real ownership: features you design end-to-end, from the Prisma schema to the React component, ship to customers within days.\nWhat you'll do\nDesign and build features across our TypeScript monorepo \u2014 tRPC procedures and NestJS services on the backend, React on the frontend.\n\n\nExtend our integration workers that sync campaign, product, and analytics data from the Google and Meta APIs via Cloud Pub\/Sub pipelines.\n\n\nWork on the AI audit agent: prompt design, rule evaluation, and the plumbing that turns LLM output into reliable, deduplicated actions \u2014 across multiple model providers, not just one.\n\n\nHelp productionize our in-house prediction models: wiring their output into the rule engine and keeping training data and evaluation pipelines healthy.\n\n\nEvolve the data model in PostgreSQL\/Prisma and keep migrations, multi-tenancy, and role-based access clean as the product grows.\n\n\nOwn quality: write Jest tests alongside your code, review PRs, and help keep our CI\/CD pipeline to Cloud Run fast and boring.\n\nOur stack\nBackend\nTypeScript \u00b7 Node.js NestJS + Fastify tRPC \u00b7 Zod Prisma \u00b7 PostgreSQL\nFrontend\nReact \u00b7 Vite End-to-end types via tRPC\nInfrastructure\nGoogle Cloud Run \u00b7 Pub\/Sub Docker \u00b7 GitHub Actions pnpm workspaces \u00b7 Turborepo\nAI & integrations\nMultiple LLM providers In-house prediction models Google Ads \u00b7 Meta Merchant Center \u00b7 GA4\nWhat we're looking for\n5+ years building production web applications, with strong TypeScript on both server and client.\n\n\nSolid relational database instincts \u2014 schema design, migrations, and query performance in PostgreSQL (Prisma experience is a plus).\n\n\nExperience with event-driven or queue-based architectures (Pub\/Sub, SQS, Kafka, or similar) and the failure modes that come with them.\n\n\nA habit of testing: you write tests because they let you move faster, not because someone told you to.\n\n\nPragmatic product sense \u2014 you ask why before how, and you'd rather ship a focused feature than a perfect abstraction.\n\nNice to have\nHands-on work with LLM APIs in production \u2014 prompting, evals, structured output, cost control, and switching between providers.\n\n\nApplied ML experience: training, evaluating, or serving prediction models alongside product code.\n\n\nFamiliarity with the Google Ads, Meta, or Merchant Center APIs, or ad-tech \/ e-commerce domain experience.\n\n\nNestJS, tRPC, or GCP (Cloud Run, Artifact Registry, Workload Identity) in a previous role.\n\nHow we work\nSmall team, short feedback loops, no ceremony for ceremony's sake. Strict TypeScript, code review on everything, CI that deploys to Cloud Run on merge. We optimize for shipping value to customers weekly and keeping the codebase a place people enjoy working in.\nOpen to all\nWe focus on your skills, not your background. We're open to adapting the role or workplace to meet your needs.","language":"sv","is_translated":true,"title_original":"Senior Full-Stack Engineer","description_original":"About agentmama\nWe build AI agents that audit and optimize e-commerce advertising. Our platform syncs live data from Google Ads, Meta, Merchant Center, and Google Analytics, runs it through a rule engine, LLM-powered audit agents, and our own prediction models, and turns the findings into concrete actions marketers can apply with one click.\nWe're a small team shipping fast on a modern, strictly-typed stack. You'd be one of a handful of engineers reporting directly to the CTO, which means real ownership: features you design end-to-end, from the Prisma schema to the React component, ship to customers within days.\nWhat you'll do\nDesign and build features across our TypeScript monorepo \u2014 tRPC procedures and NestJS services on the backend, React on the frontend.\n\n\nExtend our integration workers that sync campaign, product, and analytics data from the Google and Meta APIs via Cloud Pub\/Sub pipelines.\n\n\nWork on the AI audit agent: prompt design, rule evaluation, and the plumbing that turns LLM output into reliable, deduplicated actions \u2014 across multiple model providers, not just one.\n\n\nHelp productionize our in-house prediction models: wiring their output into the rule engine and keeping training data and evaluation pipelines healthy.\n\n\nEvolve the data model in PostgreSQL\/Prisma and keep migrations, multi-tenancy, and role-based access clean as the product grows.\n\n\nOwn quality: write Jest tests alongside your code, review PRs, and help keep our CI\/CD pipeline to Cloud Run fast and boring.\n\nOur stackBackend\nTypeScript \u00b7 Node.js NestJS + Fastify tRPC \u00b7 Zod Prisma \u00b7 PostgreSQL\nFrontend\nReact \u00b7 Vite End-to-end types via tRPC\nInfrastructure\nGoogle Cloud Run \u00b7 Pub\/Sub Docker \u00b7 GitHub Actions pnpm workspaces \u00b7 Turborepo\nAI & integrations\nMultiple LLM providers In-house prediction models Google Ads \u00b7 Meta Merchant Center \u00b7 GA4\nWhat we're looking for\n5+ years building production web applications, with strong TypeScript on both server and client.\n\n\nSolid relational database instincts \u2014 schema design, migrations, and query performance in PostgreSQL (Prisma experience is a plus).\n\n\nExperience with event-driven or queue-based architectures (Pub\/Sub, SQS, Kafka, or similar) and the failure modes that come with them.\n\n\nA habit of testing: you write tests because they let you move faster, not because someone told you to.\n\n\nPragmatic product sense \u2014 you ask why before how, and you'd rather ship a focused feature than a perfect abstraction.\n\nNice to have\nHands-on work with LLM APIs in production \u2014 prompting, evals, structured output, cost control, and switching between providers.\n\n\nApplied ML experience: training, evaluating, or serving prediction models alongside product code.\n\n\nFamiliarity with the Google Ads, Meta, or Merchant Center APIs, or ad-tech \/ e-commerce domain experience.\n\n\nNestJS, tRPC, or GCP (Cloud Run, Artifact Registry, Workload Identity) in a previous role.\n\nHow we work\nSmall team, short feedback loops, no ceremony for ceremony's sake. Strict TypeScript, code review on everything, CI that deploys to Cloud Run on merge. We optimize for shipping value to customers weekly and keeping the codebase a place people enjoy working in.\n\u00d6ppen f\u00f6r alla\nVi fokuserar p\u00e5 din kompetens, inte dina \u00f6vriga f\u00f6ruts\u00e4ttningar. Vi \u00e4r \u00f6ppna f\u00f6r att anpassa rollen eller arbetsplatsen efter dina behov.","price":null,"currency":"SEK","status":"active","noindex":true,"location":{"address":"Nybrogatan 34","full_address":null,"city":"Stockholm","country":"SE","latitude":59.337132531084,"longitude":18.079444642851},"metadata":{"region":"Stockholms l\u00e4n","duration":"Tills vidare","employer":"Agentmama AI AB","postcode":"11439","positions":1,"profession":"Backend-utvecklare","salary_type":"Fast m\u00e5nads- vecko- eller timl\u00f6n","employer_url":"https:\/\/career.agentmama.ai","scope_of_work":"100\u2013100 %","working_hours":"Heltid","contact_person":"J\u00f6rg Rosenauer","employment_type":"full_time","occupation_field":"Data\/IT","employer_workplace":"AgentMama","experience_required":true,"employment_type_label":"Vanlig anst\u00e4llning"},"user_id":null,"is_sponsored":false,"views_count":0,"ai_views_count":2,"bot_views_count":2,"ai_vendor_counts":{"anthropic":2},"visibility":"public","submission_source":null,"submission_ai_name":null,"has_owner_email":true,"can_contact_owner":true,"phone":null,"owner_email":"jorg@agentmama.ai","images":[],"published_at":"2026-09-16T22:23:42+00:00","expires_at":"2027-03-14T23:59:59+00:00","created_at":"2026-09-17T03:58:11+00:00","updated_at":"2026-09-18T03:16:21+00:00"}}