AI Engineer, Computer Vision

Niantic Spatial is seeking an AI Engineer, Computer Vision to build and iterate deep learning models for centimeter-level visual localization within its Visual Positioning System. The role spans the full lifecycle from data preparation through training and evaluation, and into production deployment.

Responsibilities

• Implement, train, and evaluate visual localization models in PyTorch, including local feature extraction and matching, image retrieval, pose regression, and scene-coordinate regression.
• Iterate on architectures, loss functions, and training loops to improve accuracy on real production captures.
• Build and maintain high-throughput ingestion and preprocessing pipelines that convert raw imagery, poses, and 3D point clouds into training-ready datasets, including curation, sampling, and augmentation.
• Run training jobs on GPU environments across a 30-billion-image corpus, coordinating with senior engineers and ML Infrastructure to keep experiments reproducible and results interpretable.
• Develop and maintain an evaluation suite for localization, including pose accuracy, recall under lighting and seasonal changes, and latency under production load, so comparisons remain consistent across model versions.
• Partner with senior engineers to move models from checkpoint to serving through export, inference optimization, and monitoring once live.
• Own model progress end-to-end, including learning from field behavior rather than only handing off checkpoints.
• Collaborate with the Research team and the Real-World Test Lab to connect field failures to training data updates and benchmark improvements.

Requirements

• Experience training deep learning models for computer vision tasks in PyTorch, gained through coursework, research, internships, or early industry work.
• Foundational understanding of at least one area: visual localization, learned feature matching, image retrieval, pose estimation, SLAM, structure-from-motion, and related 3D geometry concepts (camera models, epipolar geometry, pose parameterizations).
• Comfort working with large image or 3D datasets, including preprocessing, curation, and how data quality impacts model outcomes.
• Familiarity with GPU-based training and the ability to read and reason about training runs, including identifying bottlenecks in data loading, compute, or model design.
• Strong Python skills and a practice of writing code others can reproduce and extend.
• Bachelor’s or master’s degree in computer science, computer vision, robotics, or a related field, or equivalent practical experience.

Technologies

• PyTorch
• Python
• GPU

Nice to Have

• Published or contributed work on learned localization, visual place recognition, scene-coordinate regression, or vision foundation models (CVPR, ECCV, ICCV, NeurIPS, 3DV, or equivalent).
• Experience with large-scale self-supervised or multi-view pretraining, or fine-tuning vision foundation models for geometric tasks.
• Exposure to inference optimization for edge or mobile hardware (TensorRT, ONNX, CoreML, or similar).
• Experience with petabyte-scale spatial data including point clouds, meshes, posed image collections, or geospatial indexing.
• Background in robotics, augmented reality, 3D reconstruction, digital twins, or autonomous systems.
• Prior industry or research internship experience contributing to or shipping a production CV system.

Compensation & Benefits

Salary range: USD 165,600 - 221,000 per year.

• Annual bonus
• Equity
• Comprehensive benefits package including medical, dental, and vision coverage
• 401(k)
• More

Location & Work Model

The position is based in the San Francisco, CA office with a hybrid schedule requiring a minimum of 3 days per week in office.

Inclusive Application

Niantic Spatial encourages candidates to apply even if their experience does not match every listed qualification, as the strongest candidates do not always tick every box.