Davis AIAbout this role
Summary: The AI Engineer will build and operate multi-agent systems to transform fragmented real estate data into expert-grade deliverables. This role involves owning the end-to-end stack, including context engineering, orchestration, verification, and evaluation, to ensure production-grade quality and reliability.
TLDR; Davis is hiring an AI Engineer to work on the multi-agent pipeline turning raw, fragmented data into expert-grade real estate deliverables. You will make it more reliable, fast, and indistinguishable from the best human teams, then push it past what any human team could do, owning the stack end to end, from context engineering and orchestration to verification, storage and evaluation.
About Davis
Davis 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 Operate
Early-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 - site sourcing, feasibility studies, architectural design, investment analysis, financial modeling, dataroom analysis, and more.
The Role
You will 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.
Key Responsibilities
- 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.
What We're Looking For
- 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
- Experience operating LLM systems with observability and quality monitoring in production.
- GIS familiarity (parcels, zoning layers, geocoding).
- Multi-country product experience (heterogeneous sources, localization, varying rules).
- NLP background
Why Join Us
You're joining a team of 9 at the very beginning - where every decision you make shapes the product, the culture, and the trajectory of the company. What you build here will be yours.
- Direct impact on growth: your work doesn't sit behind three layers of review. You ship, clients use it, and you see the results. Every output you improve translates directly into revenue and reputation.
- Real-world impact: your work supports investment decisions, accelerates development timelines, and helps redefine how cities are imagined, designed, and built.
- High ownership: own the full feasibility stack end to end, as the CEO of that part.
- Competitive salary and meaningful equity in an early-stage company.
- A small team with high standards - we ship fast and love working together.
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.
Why No One Has Solved Architectural Design Yet
Real estate development bleeds time and money in architectural design loops. Architects cycle through dozens of floorplan revisions to meet regulatory and client constraints, each round taking days, each missed constraint restarting the loop. Traditional CAD and BIM tools offer zero generative capability; parametric tools only check constraints after generation, leading to designs that frequently break under new zoning rules or irregular sites.
Generative AI has the potential to solve this, but doesn't yet. Fine-tuning image diffusion models on floorplans produces layouts that look plausible but fall apart under scrutiny: hallucinated rooms, mislabeled spaces, code violations no architect would accept. Pixel-space models have no concept of what a wall is or why a corridor needs to connect two things. Compliance-guidance techniques typically require segmentation at each noisy timestep, compounding errors and making major edits impractical. As a result, floorplans may “look” plausible but break building codes, or need heavy post-processing before they're usable.
### 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.*