Machine Learning Engineer – Autonomous Perception & AI Systems

emagine Polska is a company looking for a Machine Learning Engineer to work on next-generation multi-modal perception and autonomy systems. The role involves developing advanced AI capabilities for autonomous platforms using state-of-the-art technologies in computer vision, sensor fusion, robotics, and foundation models.

• 3–5+ years of experience in Machine Learning, Robotics, Computer Vision, Artificial Intelligence, Applied Mathematics, Computer Science, or related fields.
• Strong practical experience with PyTorch and/or TensorFlow.
• Experience in end-to-end model development, training, evaluation, optimization, and productionization.
• Expertise in areas such as computer vision, autonomous systems, robotics, multi-sensor perception, reinforcement learning, Vision-Language Models (VLM), and Vision-Language-Action (VLA) systems.
• Familiarity with AI and robotics ecosystems including NVIDIA Isaac Sim/Isaac Lab, ROS2, Alpamayo, CUDA, TensorRT, synthetic data, and simulation environments.
• Strong background in linear algebra, probability and estimation theory, optimization, algorithm design, data structures, and software architecture.
• Experience developing in Python and C++.
• Ability to obtain and maintain a security clearance.

Nice to have:

• Experience developing embodied AI or autonomous robotics solutions.
• Experience with large-scale foundation models and generative AI.
• Knowledge of imitation learning, world models, or agentic AI systems.
• Experience deploying ML workloads on NVIDIA edge hardware.
• Contributions to open-source robotics or machine learning projects.

• Design, train, and optimize ML/DL solutions for multi-modal sensor fusion, 3D object detection, classification, scene understanding, semantic segmentation, object tracking, trajectory prediction, behavior modeling, and autonomous decision support.
• Develop and maintain scalable data and training pipelines including data curation, labeling, synthetic data generation, augmentation, evaluation, model monitoring, and performance optimization.
• Work with AI architectures such as Vision-Language-Action (VLA) models, foundation models for robotics and autonomy, reinforcement learning, imitation learning, and multi-modal transformer-based architectures.
• Integrate and optimize models for deployment on embedded and edge platforms including NVIDIA GPU acceleration, CUDA, TensorRT, and NVIDIA Jetson platforms.
• Ensure accurate sensor calibration, alignment, and synchronization across sensor suites mitigating drift and environmental disturbances.
• Collaborate with Systems Engineering, Planning, Controls, Robotics, and Software teams to develop safe and deployable autonomous systems.
• Investigate and evaluate emerging technologies including Alpamayo-based robotics frameworks, next-generation autonomy stacks, embodied AI, and autonomous agent architectures.

Ability to obtain and maintain a security clearance.