AI Engineer Intern

United States Digital Space LLC; Paris (TX); On-site; USD 40,000 - 60,000; Full time

Job summary

Davis AI in the United States is seeking an AI Engineer Intern to help build multi-agent systems for real-estate workflows, from context assembly to verification, storage, evaluation and observability. You will own one delivery pipeline end to end, work on context engineering, tool orchestration, and extend the evaluation harness.

You will work with French sources and deliverables and collaborate with domain experts.

Qualifications

• Experience building end-to-end data pipelines for AI systems.
• Ability to read and write French for sources and deliverables.
• Strong backend software skills with testing in Python.

Responsibilities

• Own one delivery pipeline end to end: market, financial, or regulatory analysis.
• Build the harness around the model: context engineering, tool orchestration, verification, report generation.
• Build tools agents rely on: open data sources, extraction from PDFs and plans.

Skills

Backend Python

Async

LLM pipelines

French language

Job description

TLDR; Davis AI is looking for an AI Engineer Intern to help solve one of the hardest problems in applied AI: building multi-agent systems that remain reliable across long, complex real-estate workflows. You will work on the core delivery pipeline - from context assembly and tool orchestration to verification, storage, evaluation, and observability.

About DavisDavis is an AI-native real estate company accelerating early-stage development and architectural design. Today developers coordinate 4-5 fragmented stakeholders over weeks or months. Soon they'll need only one: Davis.

We turn every input that shapes a development decision into decision-ready outputs: investor-grade feasibility studies, investment analysis, and architect-certified designs, delivered in days. Every stage pairs our proprietary AI systems with expert review, so velocity never comes at the cost of reliability.

We closed a $5.5M pre‑seed co‑led by Heartcore Capital and Balderton Capital, with Yellow, Evantic and Entrepreneur First, alongside angels from the founding teams of Spacemaker, Black Forest Labs, Hugging Face, Supabase, Cleo and Spore Bio. We already work with leading developers and expect to support hundreds of projects over the coming year, deepening our research, our hiring, and our coverage of the development process end to end.

Where We OperateEarly-stage development starts with a chain of high‑stakes decisions, each requiring different data, different expertise, and different deliverables. Today, we deliver AI‑powered outputs across the full spectrum - feasibility studies, architectural design, investment analysis, financial modeling, and more.

You will:

• Own one delivery pipeline end to end: market, financial, or regulatory analysis.
• Build the harness around the model: context engineering, tool orchestration, verification, report generation.
• Build the tools agents rely on: open data (cadastre, zoning, transactions, demographics), extraction from regulatory PDFs and plans etc.
• Turn every expert correction into source memory, gold datasets and regression evals.
• Extend the eval harness: LLM judges, replay caches, traces, prompt optimization.
• Ship production‑grade quality and reliability on every output a client receives.
• Sit with clients and domain experts, challenge your assumptions, and learn how real estate decisions are actually made.

You’ll fit right in if you:

• Write strong backend Python: clean & scalable architecture, typing, async, real tests.
• Build thin, well‑tested harness layers around LLM programs rather than stacking frameworks.
• Read and write French: our sources and deliverables are in French.
• Can sit with an architect and work out what "correct" means.

A big plus:

• Built or evaluated LLM agents in real systems; (DSPy or GEPA for ex).
• Operated long‑running, cost‑controlled LLM pipelines: caching, replay, retries, spend tracking, observability.
• GIS: shapely, projections, parcels and zoning layers, open data.
• Computational geometry or constrained optimization.
• Document understanding: PDF parsing, OCR, layout detection, plan vectorization.
• Databases and data modeling with versioning.
• Multi‑country products: heterogeneous sources, localization, varying rules.
• Interest in real estate, architecture or urban planning.

Why Davis

Build what no one has before: the system that delivers feasibility, investment analysis and design end to end

• Accelerate your craft: learn from an exceptional team while taking real ownership from day one
• Meaningful challenges: reliable agents over messy real‑world data, deployed on major construction projects
• Competitive salary
• Ship fast: prototype to production in weeks, not years
• A world‑class team of AI researchers, engineers and architects, backed by world‑class VCs

More information about Davis, the team and the market we’re going after:

Team Mehdi (Co‑founder & CEO) grew up in a family of architects and has lived this problem firsthand. He's a repeat founder who bootstrapped his first startup at 20, and graduated from Sciences Po and HEC Paris. Amine (Co‑founder & CTO) is an AI researcher from École Polytechnique who worked extensively on discrete diffusion and turned down a PhD with Google DeepMind to build Davis. They started working together in July 2025 at Entrepreneur First's first European residency, a two‑month lock‑in in a German castle.

Today we're a team of 12: technical profiles from Polytechnique, ENS and INRIA alongside architects and deep real estate expertise.

We're small with an extremely high bar. If you want to work deeply on hard problems and see your work reach clients within days, you're the one we need.

Why we’ll win

Real estate is a $13 trillion industry that technology has largely bypassed. The professional services that feed it (design, engineering, feasibility, permitting) represent hundreds of billions in spend that no one has seriously automated.

Proptech spent the last decade selling SaaS on the edges of these workflows. It didn’t work, for two reasons: no professional wants another tool to learn, and no tool can automate work that runs on expert judgment. Davis makes a different bet. We don’t sell tools, we sell the work: AI‑generated, expert‑validated, delivered in days instead of weeks. Every project compounds our data advantage across typologies, geographies and regulatory contexts.

We care about who you are, not just what's on your CV. If you're drawn to what we're building but don’t meet every requirement, we still want to hear from you. Studies show that women in particular tend to apply only when they meet 100% of the criteria. If that’s you, please don’t let that hold you back. We’d love to receive your application.