SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Material Bank is the world's largest material marketplace for architecture and design professionals, operating in 37 countries. The company is seeking a Staff Applied Scientist to build search and recommendation systems from the ground up. This is a hands-on research role where you will not hand off formulas to engineering but instead explore data, form hypotheses, prototype approaches, and prove they work before partnering with engineering for production deployment.
Key responsibilities include improving search retrieval and ranking to help members find materials and discover new options; building recommendation systems from scratch to surface intelligent suggestions across the experience; exploring behavioral and catalog data to identify which approaches fit the user base and catalog; applying advanced query understanding for diverse, real-world queries including the long tail; raising data quality to improve downstream search and recommendation quality; conducting R&D that ships by inventing and implementing formulas, models, and re-ranking approaches; iterating on visual and color-based search approaches including perceptual color matching; building evaluation frameworks and success metrics; and collaborating across product, engineering, and catalog teams.
Required qualifications include a proven track record building search, recommendations, or ranking systems that shipped to real users and moved metrics; an advanced degree in computer science, machine learning, statistics, or applied math (or equivalent hands-on experience); deep understanding of search and recommendation systems with expertise in retrieval, ranking, and relevance; strong query understanding and NLP skills including semantic and embedding-based retrieval; real exploratory and experimental rigor with statistical modeling and hypothesis testing; hands-on prototyping and implementation ability; and experience deploying ML or data systems to production.
Nice-to-have skills include experience with multimodal or image-based search, color or perceptual science, e-commerce or marketplace search experience, and managing vendor and home-grown systems together. The role is positioned as unusual because it does not plug into a mature stack with pre-decided strategy; instead, you set the approach, build it, and prove it, with a clear runway toward owning more of the search and recommendations system over time.
