Senior/Staff Machine Learning Engineer (Perception)

Join our team as a Senior/Staff Machine Learning Engineer (Perception) and be at the forefront of developing perception systems for autonomous machines. You will work on computer vision and machine learning systems that enable heavy equipment to operate safely in challenging environments. This hands-on role involves writing production-grade software, optimizing models for embedded hardware, and validating your work on real machines. You will have the opportunity to make a significant impact in the field of autonomous technology.

• Développer des modèles de perception en temps réel pour la compréhension des obstacles et du terrain dans des environnements non structurés.
• Construire une fusion multimodale qui combine les données de la caméra et du LiDAR en une représentation 3D unifiée, robuste aux occlusions.
• Optimiser les modèles pour une inférence à faible latence sur du matériel contraint en ressources, en équilibrant précision et performance.
• An eagerness to get your hands dirty and agility in a fast-moving, collaborative, small team environment with lots of ownership
• Strong grounding in multi-sensor integration (camera, LiDAR, radar): calibration, spatiotemporal sync, and cross-modal fusion
• Deep expertise developing and deploying modern perception models: detection, segmentation, mono/stereo/metric depth, BEV/occupancy, sensor fusion, and 3D scene understanding
• Experience handling large datasets efficiently and organizing them for labeling, training and evaluation
• A MS/PhD in Computer Science, AI, or a related field, or 6+ years of industry experience building vision-based perception systems
• Proven ability to design experiments, analyze metrics (mAP, IoU, latency/throughput, and calibration/ECE), and optimize to meet stringent real-world performance and safety requirements
• Fluency adapting, fine-tuning, and distilling large pre-trained vision and vision-language models
• Fluency in Python with PyTorch/TensorFlow/OpenCV and the ability to write efficient, production-ready code for real-time systems
• Experience architecting multi-sensor ML systems from scratch
• Experience building auto-labeling / data-engine flywheels at scale
• Experience with compute-constrained pipelines including optimizing models to balance the accuracy vs. performance tradeoff, leveraging TensorRT, model quantization, etc
• Familiarity with emerging predictive world models for anticipation, anomaly detection, or closed-loop simulation, and adjacent policy paradigms such as Vision-Language-Action (VLA) and World-Action (WAM) models
• Publications at top-tier perception/robotics venues (CVPR, ICRA, CoRL, RSS, etc.)
• Experience with compute-constrained deployment: TensorRT, model quantization, and custom CUDA operations
• Passion for how we feed, build, move, and maintain the world