Staff Perception Scientist

What you'll do

• Develop innovative methods for detection, segmentation, tracking, localization, scene understanding, and multimodal sensor fusion.
• Formulate research questions and design controlled experiments to translate ideas into robust production algorithms.
• Advance model architectures that remain accurate under motion, occlusion, domain shift, and sensor degradation.
• Define datasets, labeling strategies, metrics, benchmarks, and evaluation protocols for real-world product requirements.
• Build reproducible training pipelines and investigate failure modes using quantitative evidence.
• Optimize models for latency, power, memory, and accuracy across Arm CPUs and heterogeneous AI accelerators.
• Integrate perception pipelines with sensor I/O, runtimes, robotics middleware, and downstream consumers.
• Create reference implementations and diagnostics to make perception behavior observable and testable on-device.

What we're looking for

• 6+ years of experience in applied perception, computer vision, machine learning, or a related field.
• 3+ years of experience moving perception research into real-time or production systems.
• Proficiency in Python and C++ with PyTorch, JAX, TensorFlow, or similar frameworks.
• Strong understanding of deep learning for multimodal perception, probability, optimization, 3D geometry, and sensor fusion.
• Knowledge of efficient inference, numerical precision, model compression, and edge deployment constraints.
• Ability to design rigorous experiments and communicate results to research, engineering, and product audiences.
• PhD or equivalent experience in computer vision, machine learning, robotics, computer science, or a related field (preferred).
• Experience with 3D perception, SLAM, multimodal models, or heterogeneous accelerators (preferred).