Robert van Dijk
Ai Solutions Scientist @Cellvoyant
Signup · Get unlimited contacts
WORK HISTORY
Ai Solutions Scientist @Cellvoyant
Lead the translation of biological workflows into deployable machine learning solutions, operating at the interface of biology, engineering, and commercial teams- Identify and address gaps between R&D and Business Development, shaping solution strategy, technical discovery, and partner delivery- Define data acquisition strategies and experimental requirements to ensure biological datasets are suitable for robust machine learning modelling- Design, develop, and validate AI models for cell therapy applications, with a focus on image-based and multimodal representations of cell state- Work directly with external partners to scope problems, develop solution architectures, and translate model performance into expected experimental and business impact- Drive rapid iteration of proof-of-concept models into production-ready systems, incorporating feedback from both biological and commercial stakeholders- Contribute to technical communication, including case studies and materials that articulate platform capabilities and real-world value.
EDUCATION
Stedelijk Gymnasium Breda
Pre-university education (inc. Latin and Greek), N&T
Eindhoven University of Technology
Biomedische technologie (Biomedical engineering)
Eindhoven University of Technology
Master of Science in Engineering, Medical Engineering
ABOUT ROBERT VAN DIJK
I work at the intersection of biology and machine learning, focusing on turning complex biological systems into deployable, real-world AI solutions.My work is centred around a simple idea: biological data is only as useful as the systems built around it. In practice, this means designing experiments with modelling in mind, understanding where biological variability breaks assumptions, and building machine learning systems that remain robust under real-world constraints.At CellVoyant, I collaborate closely with biologists, engineers, and external partners to translate biological processes into technical frameworks. This includes shaping data acquisition strategies, building and validating models, and delivering systems that support decision-making in cell-based development. My work spans multimodal and image-based modelling, representation learning, and production-ready ML pipelines.I am drawn to biology because of its complexity—systems with many unknowns and high variability, yet governed by underlying structure. What I find compelling is that these systems are not arbitrary; once understood, they become coherent. This is where I see data-driven machine learning approaches as especially powerful: uncovering structure in high-dimensional, noisy systems where relationships are not immediately visible.I am interested in problems where biology and machine learning must co-evolve—where progress depends not just on better models, but on tighter integration between experimental design, data generation, and computational methods. This motivates my interest in areas such as multimodal modelling, representation learning, and data-centric approaches to complex biological systems.More broadly, I care about translating scientific progress into real-world impact. I believe that for advances in biology to be widely adopted, they must be usable, scalable, and ultimately commercially viable.I enjoy working in multidisciplinary environments, take ownership across the full lifecycle of a project, and am motivated by solving problems at the boundary of what is currently understood.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.