PixelVision - Data Scientist

PixelVision focuses on Leveraging remote imaging and AI-based analytics to revolutionize operations and maintenance of industrial assets

You can view the website at http://www.pixelvision.io. The company is supported by serial entrepreneurs from Oxford University with many accolades.

What you would do

Our cloud platform ingests remote imaging data as raw material to produce maps and 3D models that provide actionable intelligence to businesses. We are hiring a Data Scientist to help develop modular and robust data analysis tools and products.

Responsibilities (indicative, non-exhaustive)

- You will be responsible for leading a team of data scientists, and engineers specializing in deep learning, image processing, and geomatics, and in charge of R&D on data analysis tools deployed on our platform.

- Collaborate with the rest of the engineering team to design and launch new features.

- Maintain code integrity and organization.

- You can operate effectively at a fast-paced company and embrace change.

- You are curious and pragmatic

- Agile Mindset

- Expertise in managing following inputs datasets, Images of drones, LIDAR point clouds, CAD model

- Deep learning applied to 3D data Your main task will be to design algorithms for the semantic segmentation of cloud points. Point clouds from LIDAR sensors and/or photogrammetric processing generally have large sizes and require robust and efficient algorithms to be analyzed.

Must have

- Ph.D. in Computer Science or equivalent combination of degree and relevant experience with thesis/specialization in Image Analysis (preferably with following datasets: images of drones, LIDAR point clouds, or CAD models)

- 3+ years of industry experience

- Strong background in Machine Learning/Deep Learning

- Ability to read, understand and implement research papers

- Language: Python

- Experience with a machine learning library (PyTorch, Tensorflow, sklearn)

- Experience in implementing techniques in image segmentation and object detection like Faster R-CNN, hierarchical multi-scale attention for semantic segmentation, end-to-end object detection with transformers, deep nets, 3D CNN, point-net, CNN graphs, etc.

Strong preference for candidates familiar with

- PointNet ++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space:

https://arxiv.org/abs/1706.02413

- KPConv: Flexible and Deformable Convolution for Point Clouds:

https://arxiv.org/abs/1904.08889

- PyTorch Points 3D: https://github.com/nicolas-chaulet/torch-points3d

Desired characteristics

- You can operate effectively at a fast-paced company

- Curiosity and pragmatism

- Agile mindset

- Comfort with uncertainty, self-starter with lots of initiative

- Strong sense of responsibility, ownership, and accountability

Please fill the form https://forms.gle/fkKmNVnPgYJogm4n7

Salary: Negotiable