Meetdavis
AI Engineer - Full time
Опубликовано
- География
- Paris
- Опыт
- От 1.5 лет
- Занятость
- Полная занятость
Актуальность нужно проверить
Откройте публикацию в источнике и уточните, продолжается ли набор.
Источник проверяли 14 ноября
Доступ проверим при нажатии.
О вакансии
Вакансия «AI Engineer - Full time» в компании Meetdavis. Место работы: Paris.
Чем предстоит заниматься
- work on one of the core systems behind what Davis delivers. Our agents take raw, fragmented data and turn it into deliverables that real estate professionals use to make high-stakes decisions. Your job is to make that pipeline reliable, fast, and indistinguishable from work done by the best human teams - then push it beyond what any human team could do.
- You can expect to
- Build and operate multi-agent systems that turn heterogeneous data into expert-grade deliverables across real estate development workflows.
- Own the system end to end: infra, orchestration, context engineering, how the system selects, structures, and injects the right information so agents behave reliably at scale.
- Ensure production-grade quality, performance, and reliability across every output we deliver to clients.
- Sit with clients and domain experts regularly to understand their constraints, challenge your own assumptions, and make sure every output meets and even exceeds clients' expectations.
- Beyond the technical depth, this role will expose you to how real estate decisions are made, how clients think, and what it takes to deliver outputs they trust. You'll develop a sharp business intuition alongside your engineering skills.
- Harness engineering: design and build the system layer around the model - context assembly, tool orchestration, verification, and report generation - to deliver consistent, high-quality outputs at scale.
- Data ingestion & context assembly: handle messy, unstructured project data from heterogeneous sources and ensure agents have the right context at all times.
- Storage & traceability: persist sources, extracted facts, intermediate results, report versions, and expert edits.
- Expert-in-the-loop UX: design and build the review experience (annotations, edits, approvals, diffs/version history, provenance display).
- Evaluation & benchmarking: build an internal eval harness (datasets, rubrics, regression tests, monitoring) to track agents performance over time.
Что нужно для работы
- 1.5+ years building and deploying production software at scale (APIs, reliability, testing, performance).
- Experience building and evaluating LLM agents / multi-step workflows in real systems.
- Proven context engineering experience: you've built systems where reliability depends on assembling the right context (RAG over heterogeneous sources, summarization, conversation state, tool outputs).
- Deep Python expertise (clean architecture, typing, async/concurrency, strong testing culture).
- Strong experience with databases + data modeling (structured storage, document storage, versioning).
- Full-stack experience (you can ship a real UI), with a clear backend emphasis.
- Comfortable building from first principles: we don't want heavy agent frameworks — we prefer a lightweight, well-engineered codebase.
- Nice to Have
- Будет плюсом: Experience operating LLM systems with observability and quality monitoring in production.
- Будет плюсом: GIS familiarity (parcels, zoning layers, geocoding).
- Будет плюсом: Multi-country product experience (heterogeneous sources, localization, varying rules).
- Будет плюсом: NLP background
Источник: Arbeitnow. Условия и актуальность вакансии подтверждает работодатель.
Подходит вакансия?
Перейдите к исходному объявлению или контакту работодателя.
Доступ проверим при нажатии.