🛠 Tech Stack

💼 About This Role

You'll bridge 3D computer vision and large language models to create a unified framework for spatial reasoning. Your core impact will be enabling systems to perform context-aware navigation and answer complex questions about the physical world. This role stands out for building the geospatial AI foundation at a company with a proprietary database of over 30 billion posed images.

🎯 What You'll Do

• Lead cross-modal grounding between 3D features and language embeddings.
• Develop algorithms for continuous semantics in 3D maps.
• Build spatial reasoning systems for Embodied AI.
• Define benchmarks for measuring spatial common sense in LLMs.

📋 Requirements

• PhD in Computer Vision, Machine Learning, or Robotics with focus on multimodal understanding.
• 4+ years of ML research with models bridging 3D Vision and Language.
• Expert knowledge of 3D Geometry (SfM, SLAM, VPS) and Transformer-based architectures.
• Multiple first-author publications at CVPR, NeurIPS, or ICLR.

✨ Nice to Have

• Experience with Gaussian Splatting or NeRFs.
• Background in robotics (ROS) or agentic systems.
• Experience with open-set recognition or Zero-Shot learning.

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 🏥 Comprehensive health insurance
• 💰 Equity packages
• 🍱 Daily catered lunch
• 🎓 Learning & development budget

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3On-site Interview· 4 hours