Founding AI Engineer [LLM Platform]

ppbZurich HQ /b | bEarly Equity /b | bHigh Velocity /b /p h3Founding AI Engineer (LLM Platform) /h3 h3The Mission /h3 pOver $300B+ in complex travel bookings still depend on manual workflows. While the world moved to APIs, high‑stakes bookings (weddings, conferences, group travel) are still handled by humans manually typing data from messy emails into legacy systems. /p pbLobby is the orchestration layer that fixes this. /b We are not building a chatbot; we are building AI agents that negotiate, quote, and execute transactions directly within the core infrastructure of global travel brands. /p h3The Challenge /h3 pAs our Founding AI Engineer, you do not “integrate an API and call it AI”. You own the intelligence layer of a production system that enterprises depend on. You will: /p ul libRun the Engine: /b Take ownership of our existing LLM orchestration engine and evolve it, from prompt architecture to state handling to failure recovery. /li libScale per Client: /b Set up and manage dedicated model instances and configurations for each enterprise client, and build the tooling that makes onboarding the next ten clients boring. /li libMaster Model Switching: /b Route between models and providers based on task, latency, and cost. Swap models under the hood without breaking client-specific behavior. /li libOptimize Relentlessly: /b Own the cost and performance curve of every token we spend. Build evals that catch regressions before customers do. /li /ul h3Your Stack /h3 pWe value boring technology used for exciting problems. We optimize for shipping speed: /p ul libCore: /b Python (FastAPI/Django), PostgreSQL, Redis. /li libThe AI Layer: /b Multi-provider LLM integration, custom orchestration logic, prompt pipelines, eval harnesses. /li libInfrastructure: /b AWS, Docker. /li libObservability: /b Tracing, cost tracking, and eval dashboards you will help shape. /li /ul h3Must Haves /h3 ul libSeasoned Builder: /b Minimum 8 years of experience as a software engineer (fullstack, or at least more backend / infra heavy). /li libStartup DNA: /b You have worked at a startup before, in a small team, and you know what it means to ship without layers of process around you. /li libEngineer First: /b You are a software engineer who transitioned into AI, not a data scientist who learned to deploy. You think in production systems, not notebooks. No PhD required or expected. /li libBattle‑Tested in AI: /b You have shipped and operated complex AI setups in production. Multi-step agent flows, per-tenant configurations, real users, real failure modes. Not just a thin wrapper around a chat endpoint. /li libEvals as a Discipline: /b You treat prompt engineering and evals as engineering, with versioning, regression testing, and measurable outcomes, not vibes. /li libProven, Not Self-Declared: /b You can point to systems you have built and run, not just talks you have given. We hire evidence, not job titles. /li libSwiss‑Based/Local: /b You want to be on the ground in Zurich, building alongside the founders in a high‑intensity environment. /li /ul h3Why Lobby? /h3 ul libFounding Equity: /b We want you to be a multi‑millionaire if we succeed. You get a seat at the table, not just a desk. /li libExtreme Autonomy: /b No "Middle Managers." No "Agile Coaches." Just builders, customers, and code. /li libMarket Pull: /b We are tackling a massive, un‑sexy problem that is desperate for a modern solution. The "Why Now" is obvious once you see the product. /li /ul h3How to Apply /h3 pDo not send a formal cover letter. Send us: /p ul liA link to an AI system you built or operated in production (repo, write‑up, or demo). /li liThe gnarliest model, prompt, or scaling problem you have solved, and how you knew it was actually fixed. /li /ul pEmail: /p /p