Data Scientist

About Huspy

Huspy is a proptech company operating across the EMEA region and building technology to modernize the home-buying experience. Founded in 2020, the company now works in several cities in the UAE and Spain, and is also expanding into Saudi Arabia plus three additional European markets by 2026.

The business currently holds the largest share of the UAE mortgage market and has become one of the fastest-expanding players in every European city it has entered. It has secured more than $140 million across Series A and Series B rounds from investors such as Sequoia Capital, Founders Fund, and Balderton Capital. Its SuperApp supports real estate agents and mortgage brokers with technology designed to make property transactions faster and more effective.

Role Overview

As a Data Scientist, you will help build data-driven solutions for real estate and mortgage use cases, from modeling and experimentation to production deployment. The role combines applied machine learning, data analysis, and cross-functional collaboration to support business growth and product performance.

What You Will Do

• Develop predictive models for real estate challenges such as valuation and pricing, using traditional supervised learning methods as well as more advanced machine learning techniques.
• Design multimodal embeddings for real estate entities, including listings that combine images, text, and structured attributes, to improve search, matching, deduplication, and recommendations.
• Work with SQL and Python to pull, clean, and analyze data, and set up experiments to measure product and model impact using strong evaluation metrics.
• Move models into production with support for monitoring, automated deployment, rollout processes, and CI/CD practices in collaboration with engineering teams.
• Partner closely with product, engineering, and operations stakeholders to turn business needs into scalable machine learning solutions.

What You Need

• 4 to 8 years of hands-on experience in applied data science or machine learning, with a track record of delivering models that improve business outcomes.
• Strong command of SQL and Python, along with libraries such as Pandas, NumPy, and Scikit-learn for data pipelines, model training, and evaluation.
• Practical understanding of MLOps concepts, including batch or real-time deployment, model versioning, CI/CD basics, monitoring, and reproducible training.
• Ability to communicate effectively with both technical and non-technical audiences, and to prioritize work while explaining trade-offs clearly.
• Comfort dealing with ambiguity, imperfect data, leakage concerns, and changing market conditions such as location trends, seasonality, and inventory movement.
• Preferred additions include software engineering experience, exposure to multimodal or computer vision work, and familiarity with voice AI such as ASR or NLU.
• A bachelor’s degree in a STEM discipline is required; a master’s degree is considered an advantage.

Additional Information

By applying, you consent to your personal data being collected, processed, and retained by the company for the purpose of evaluating and managing your application.