The GeoAI team is building next-generation AI-powered data automation platforms for ADAS and autonomous driving. We are seeking a Machine Learning Engineer to develop scalable auto-labeling technologies that transform fleet-collected sensor data into high-quality training datasets with minimal human intervention. 

This role sits at the intersection of machine learning, computer vision, spatial AI, and large-scale data infrastructure. You will work on perception models, 3D scene reconstruction, foundation models, and automated data-generation systems that accelerate autonomous-driving development. 

The Role:

Build Next-Generation Auto-Labeling Systems 

• Design and deploy production-scale auto-labeling solutions for 2D and 3D object detection, semantic and panoptic segmentation, lane and road-structure extraction, multi-object tracking, occupancy, scene understanding, and traffic-participant behavior. 
• Develop automated label validation, confidence scoring, consistency checks, and quality-monitoring frameworks. 
• Build active-learning and human-in-the-loop workflows that improve label quality while reducing manual annotation effort and turnaround time. 
• Create teacher-student and model-assisted labeling workflows for large-scale camera and LiDAR datasets. 

Develop Advanced Perception and Fusion Models 

• Research, train, and evaluate camera-based and LiDAR-based detection, segmentation, tracking, depth-estimation, and occupancy models. 
• Develop multimodal fusion models combining camera, LiDAR, radar, GNSS/IMU, and map context. 
• Improve temporal consistency, calibration robustness, and long-tail performance across diverse driving environments and edge cases. 
• Build end-to-end ML workflows from raw sensor ingestion and preprocessing through annotation, quality control, and dataset delivery. 

Leverage Spatial AI and 3DGS 

• Develop 3D Gaussian Splatting (3DGS) and related reconstruction pipelines for large-scale driving scenes collected from fleet vehicles. 
• Use reconstructed scenes for label propagation, synthetic annotation generation, annotation validation, rare-case augmentation, and simulation. 
• Create scene-centric representations that improve geometric accuracy and consistency across sensors, viewpoints, and time. 

Apply Foundation Models to Data Automation 

• Apply Vision-Language Models (VLMs), Vision-Language-Action (VLA) models, and multimodal foundation models to scene interpretation, label generation, verification, and edge-case discovery. 
• Develop natural-language and agent-based workflows that help engineers search, inspect, curate, and validate large-scale datasets. 
• Evaluate state-of-the-art research and convert promising methods into reliable production capabilities. 

Productionize ML Solutions 

• Build scalable training and inference pipelines for fleet-scale datasets and distributed GPU infrastructure. 
• Optimize model performance, throughput, reliability, monitoring, and reproducibility across cloud and production environments. 
• Collaborate with perception, mapping, navigation, simulation, hardware, logging, and data-platform teams to deploy end-to-end solutions. 
• Define and track metrics for labeling accuracy, coverage, throughput, cost, and operational efficiency. 

Qualifications:

• MS or PhD in Computer Science, Machine Learning, Robotics, Computer Vision, or a related field. 
• Strong software-engineering skills in Python and/or C++, with hands-on experience using PyTorch or equivalent deep-learning frameworks. 
• Solid understanding of deep learning, computer vision, 3D geometry, multi-view reconstruction, sensor fusion, and transformer architectures. 
• Experience developing detection, segmentation, tracking, depth, occupancy, or multimodal perception models. 
• Experience building, evaluating, and deploying machine-learning systems using large-scale datasets. 
• Ability to work independently and collaborate effectively across research, software, data, and vehicle teams. 

Preferred:

• Experience in autonomous driving, robotics, mapping, AR/VR, or spatial computing. 
• Hands-on experience with 3DGS, NeRF, neural rendering, world models, or synthetic data generation. 
• Experience building auto-labeling platforms, active-learning systems, human-in-the-loop workflows, or automated label-quality systems. 
• Experience with camera-LiDAR fusion, depth estimation, 3D detection and tracking, and multimodal foundation models. 
• Familiarity with VLMs, VLA models, SAM-family segmentation models, distributed computing, Docker, Kubernetes, CI/CD, and cloud ML infrastructure.