Senior ML Data Scientist - Wireless People Sensing

Algorized is a VC-funded Silicon Valley deep-tech company with Swiss roots. We build edge-AI models that give robots real-time awareness of people using existing wireless sensors, enabling safer human–machine collaboration.As we continue to scale, we are looking for a Senior Data Scientist who is passionate about innovation, applied research, and turning complex sensing challenges into robust products. If you thrive in a dynamic startup environment, take ownership, and enjoy working across data science, signal processing, and product development, we would love to meet you.This is a hybrid or on-site position based in Etoy, Switzerland. Fully remote arrangements are not available. Candidates must be legally authorized to work in Switzerland.Role OverviewThis is a hands-on senior role with significant technical ownership. You will be a key contributor to the development of foundational models for wireless people sensing, working with raw radar and other wireless sensor signals to build models that generalize across environments, devices, and real-world use cases.You will combine modern data science and machine learning with strong signal-processing expertise using various sensor modalities. Working closely with engineering and product teams, you will help shape our modeling strategy, lead experimentation, and translate research ideas into reliable people-sensing capabilities.Key ResponsibilitiesDesign, develop, and improve machine-learning models and algorithms for wireless people sensing using radar and other sensor signals.Play a key role in developing foundational models that can support multiple people-sensing tasks, environments, and sensor configurations.Develop signal-processing, machine-learning, and deep-learning methods that transform wireless sensor signals into accurate and robust people-sensing outputs.Design model architectures and learning approaches that capture spatial and temporal patterns in wireless sensor data.Design experiments, define evaluation methodologies, and analyze model behavior, limitations, and generalization.Evaluate and adapt relevant advances in time-series and representation learning to improve model accuracy, robustness, and generalization across environments and sensor configurations.Cross functional collaboration with software engineers and MLOps in infrastructure development.Mentor junior team members and contribute to the technical direction and data-science practices of the company.Minimum QualificationsPhD in Data Science, Computer Science, Wireless Communication, Electrical Engineering, Applied Mathematics, Physics, or a related quantitative field.At least 3 years of hands-on experience developing machine-learning or data-science solutions for real-world applications.Proven expertise in data science and machine learning, with experience applying statistical and learning-based methods to sensor or time-series data.Strong knowledge of signal-processing principles and practical experience applying methods such as spectral analysis, filtering, estimation, detection, tracking, or sensor fusion.Strong understanding of machine-learning fundamentals, including model development, evaluation, optimization, and generalization.Strong Python skills and practical experience with frameworks such as PyTorch, scikit-learn, NumPy, and SciPy.Ability to take ownership of open-ended technical problems and move effectively from exploration to validated solutions.Excellent collaboration and communication skills, with genuine enthusiasm for solving challenging people-sensing problems.Preferred QualificationsExperience with radar, RF sensing, LiDAR, computer vision, acoustics, or other sensing modalities.Experience designing experiments and working with complex, noisy, or imperfect real-world data.Familiarity with self-supervised learning, representation learning, multimodal models, or foundation-model development.Experience with 3D positioning, occupancy sensing, human activity recognition, tracking systems, or vital-sign estimation.Familiarity with edge-AI constraints and the trade-offs involved in moving models from research into production.Experience collaborating across data science, embedded, software, and product teams. #J-18808-Ljbffr