Founding Engineer, AI Systems & Infrastructure
hace 8 días
Madrid
ppbFirmwork /b is building the bexecution layer for AI-native firms. /b /p pExpert firms still run on inboxes, folders, documents, spreadsheets, meetings and people’s memory. AI has entered the firm, but mostly as a tool sitting outside the real work: a chatbot, a drafting assistant, a search box. /p pThat is not enough. /p pThe real shift is turning the firm itself into an AI-native operating system: matters, documents, decisions, approvals, workflows and institutional knowledge connected in one controlled layer where agents and humans can work together. /p pFirmwork is building that layer. /p pWe started in legal, where the pain is obvious: MA deals involve thousands of documents, complex diligence, drafting, negotiation, status tracking, client updates, approvals and high-stakes judgment. Our platform gives teams a workspace where agents can read the matter, operate on documents, produce work product, cite sources, propose changes, branch/merge work, and stay under human supervision. /p pNow we are deploying this inside real firms and adjacent expert workflows: law firms, private capital, family offices and operating businesses that want to become AI-native from the inside. /p pWe are hiring a Founding Engineer to build the infrastructure behind that. /p h3What you’ll build /h3 pYou will work directly with the founder to build agentic infrastructure for real professional work. /p ul liAgent runtimes that can operate over real files, workflows and user intent. /li liVirtual file systems for matters, projects and firm knowledge. /li liBranching, merging, review and approval flows for AI-generated work. /li liDurable workflows with retries, persistence, observability and human checkpoints. /li liSandboxed execution environments for agents. /li liSecure multi-tenant infrastructure with permissions, audit logs, secrets and data boundaries. /li liDocument pipelines for PDFs, DOCX, spreadsheets, data rooms and generated work product. /li liIntegrations with Google Drive, Microsoft 365, storage systems and internal firm workflows. /li liBackend systems that make AI agents reliable enough to use in serious environments. /li /ul pThis is not a normal full-stack role. /p pThe frontend and product surface matter, and we care deeply about taste. But the biggest need is infrastructure: backend architecture, security, reliability, workflow orchestration, agent execution, data models, permissions, deployment and systems thinking. /p pYour job is to double our technical velocity and raise the quality of the infrastructure underneath everything we ship. /p h3What we are looking for /h3 pYou might be a fit if you: /p ul liAre excellent at TypeScript, backend systems and product engineering. /li liHave built real software that had to be reliable, not just demos. /li liUnderstand databases, queues, storage, auth, permissions, APIs, observability and deployment. /li liHave strong instincts around security, tenant isolation, auditability and data boundaries. /li liAre excited by AI agents, tool use, workflow engines, sandboxes and human-in-the-loop systems. /li liUse AI tools aggressively in your own work, but do not confuse speed with sloppiness. /li liCan sit with users, understand messy workflows, and turn them into clean infrastructure. /li liWant founder-level ownership, not a narrow engineering ticket queue. /li /ul pYou do not need to know legal. You do need to care about understanding complex work deeply enough to automate it responsibly. /p h3Our stack /h3 pWe currently work with: /p pNext.js, React, TypeScript, Vercel AI SDK, Vercel Workflows, Vercel Sandbox, Postgres, AWS, WorkOS, Upstash, Trigger.dev, Google/Microsoft APIs, PDF/DOCX tooling and custom agent infrastructure. /p pYou do not need to have used every tool. You need to be able to reason from first principles and learn fast. /p h3First 90 days /h3 pDays 1-30: Understand the Firmwork framework, the product, current deployments, user workflows, the agent runtime and the infrastructure underneath it all. /p pDays 31-60: Own a specific slice of production, taking one runtime, workflow or product surface from problem framing through implementation, deployment and review. /p pDays 61-90: Spearhead real innovation in the legal field around agentic harnesses: own infrastructure deployment and the application layer end to end while shipping valuable production workflows for users. /p /p #J-18808-Ljbffr