Computer Vision Engineer

We are seeking a skilled Computer Vision Engineer to join our team and work on high-impact geospatial analysis using drone imagery. This role involves fine-tuning cutting-edge zero-shot object detection and depth estimation models, building reproducible evaluation pipelines, and contributing to wildfire risk analysis aligned with CalFire and IBHS criteria.

Responsibilities:

• Fine-tune and benchmark zero-shot object detectors (e.g., Grounding DINO, OV-DINO) and depth estimation models on high-resolution drone imagery

• Integrate DSM/DTM data layers for more precise and contextualized depth estimation

• Build reproducible evaluation notebooks and visualizations, mapping model outputs to wildfire resilience frameworks (CalFire/IBHS)

• Collaborate with geospatial and wildfire risk experts to ensure model alignment with operational criteria

• Transition to closed-set object detection models as annotated pilot datasets become available

• Maintain code quality, version control, and reproducibility standards

Requirments: 

• Strong experience in deep learning for computer vision, specifically object detection and depth estimation

• Proficiency with zero-shot detection frameworks such as Grounding DINO or OV-DINO

• Familiarity with geospatial data and digital surface/terrain models (DSM/DTM)

• Proficient in Python, PyTorch, and relevant libraries (e.g., OpenCV, torchvision, MMDetection)

• Experience building and maintaining Jupyter-based evaluation pipelines

• Strong data visualization skills (e.g., Matplotlib, Plotly, or similar)