The Role
Develop and scale state-of-the-art computer vision pipelines for aerial and oblique imagery. Train and improve segmentation, detection, and generative models, run large-scale PyTorch experiments, maintain modular ML infrastructure, and collaborate on deployment and inference optimizations while reproducing top-tier research.
Summary Generated by Built In
ABOUT DURANTA & WHAT WE’RE LOOKING FOR
Duranta is an applied research lab actively redefining how industries interact with the physical world through Artificial Spatial Intelligence. Our flagship foundation computer vision model, Aidan, measures and understands the world in 4D. Duranta’s founding team have built unicorns, had successful exits and published groundbreaking research within the field of computer vision. We are seeking a Senior Computer Vision Engineer to join our team.
We are a seed-stage startup building cutting-edge computer vision and generative modeling systems to understand the physical world from aerial and oblique imagery. Our team includes award winning engineers and scientists (Forbes AI 50, CVPR, SIGGRAPH) with backgrounds from Stanford, UC Berkeley, CMU, EPFL, NYU, ASU and University of Toronto. We’re working on developing a modular, scalable ML pipeline to power broad geospatial intelligence.
You will work closely with the founding team on deep learning research and deployment across semantic and instance segmentation, few-shot learning, 3D reasoning and generative modeling. Specifically, you will be responsible for contributing to the development of our computer vision pipelines for extracting comprehensive intelligence from aerial imagery.
RESPONSIBILITIES & FOCUS AREAS
- Building the components of a state-of-the-art computer vision pipeline for our AI system
- Build and improve CV models (e.g., Mask2Former, SAM, ViT, Swin) for aerial and oblique imagery
- Run experiments at scale with deep learning frameworks like PyTorch
- Develop and maintain clean, modular ML infrastructure
- Collaborate on model deployment and inference optimizations
- Read and reproduce ideas from latest papers (CVPR, NeurIPS and other similar top-tier venues)
YOU WILL THRIVE IF YOU HAVE
- Have 5+ years experience in ML / deep learning, ideally in Computer Vision
- Have strong coding ability (Python, PyTorch)
- Have trained segmentation/detection models on real-world data at scale
- Have experience with generative modeling and large foundation models
- Have worked in startups or fast-moving teams and can wear many hats
AND FOR EXTRA CREDIT…
- Experience with high-res aerial/remote sensing imagery and LiDAR
- Experience with self-supervised and weakly-supervised learning
- Knowledge of 3D, CAD and computer graphics
- Experience with cloud computing (e.g., AWS)
DURANTA VALUES
- API = Assume Positive Intent. The company, the relationship with co-workers and customers, and life is so much better and more fun if you follow this rule.
- Speed is the essence. We are in a hurry to make a difference.
- Expect Peak Performance. We strive for excellence and empower those around us to do the same.
- Build something beautiful. A beautiful product, a beautiful company, and a more beautiful world.
Skills Required
- 5+ years experience in ML / deep learning, ideally in Computer Vision
- Strong coding ability in Python and PyTorch
- Trained segmentation and detection models on real-world data at scale
- Experience with generative modeling and large foundation models
- Experience working in startups or fast-moving teams and ability to wear many hats
- Experience with high-resolution aerial/remote sensing imagery and LiDAR
- Experience with self-supervised and weakly-supervised learning
- Knowledge of 3D, CAD, and computer graphics
- Experience with cloud computing (e.g., AWS)
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
There are over 300 million acres of urban dwelling space in the US, with 1.5 million acres a year added to that number. We build the tools that allow landscapers to design, install and maintain beautiful outdoor spaces
.jpg)
