The posting
We are building a next-generation real estate investment platform, replacing manual processes and scattered PDFs with reliable data and intelligent automation. Think of us as an automated matchmaker: we pair land plots with compatible house designs, optimizing for budgets, zoning rules, and investor goals at scale.
In this role, you will own the intelligence layer of our platform end-to-end, turning unstructured floor plans, technical drawings, and inclusion lists into clean, validated, and traceable data that powers our core recommendation engine.
When you join us, you will:
-Design, build, and ship AI/ML features end-to-end, from early prototypes to production monitoring and background jobs.
-Improve geometry extraction from floor plans and land plots using Computer Vision (OpenCV, PyTorch) combined with advanced OCR on messy PDFs, tables, and scans.
-Build agentic workflows, RAG systems, and LLM solutions with strict output structuring, source citations, and hybrid search capabilities.
-Establish robust evaluation frameworks to measure prompt and model performance, while keeping latency and external API costs under control.
-Collaborate with product and engineering to integrate extracted intelligence directly into our backend ecosystem (SQL/PostgreSQL, spatial data, vector databases).
MUST-HAVES
5+ years building data or ML systems, with at least one AI feature taken to production and maintained.
-LLMs & RAG: Real-world experience with prompt design, structured outputs, agentic workflows, evaluation, chunking, embeddings, vector/hybrid search, and re-ranking.
-Computer Vision & OCR: Strong hands-on experience in document understanding on complex/messy PDFs, tables, image processing, detection, or segmentation.
-Backend & Data Engineering: Solid proficiency in Python, SQL, PostgreSQL, and comfort navigating an established backend codebase.
-Proven ability to solve complex problems independently while dealing with highly unstructured data.
NICE TO HAVES
-Experience with technical drawings, site plans, or geometric data processing (PostGIS, spatial queries).
-Familiarity with Elixir / Phoenix (or willingness to learn).
-MLOps experience (Google Cloud, Fly.io).
-Background in proptech, construction, or fintech.
Ambush is a people first company where talented, thoughtful individuals come together to build meaningful products and lasting partnerships. We believe the best work happens when people feel supported, trusted and empowered to bring their full abilities to the table. Since 2015, because of our people first and long term mindset, we have grown into a partner relied on by some of the best companies in the world. We combine strong engineering, design and strategy with a growing strength in AI to help our clients see what is next and achieve bigger outcomes. At the heart of everything we do is our team. We collaborate, take risks, lift each other up and take pride in doing work the right way, not settling for a quick makeshift solution. If you join Ambush, you join a group of people who want you to succeed and who show up for each other every day. We believe in and expect real teamwork, a constant drive to be better, and delivering meaningful long term outcomes that we can be proud of together.



