Computer Vision Scientist

Orbital Insight Boston , MA 02298

Posted 2 months ago

Computer Vision Scientist

Our mission is to understand the Earth, including all of the economic and social trends impacting us. We use computer vision, deep learning and statistical machine learning to extract useful patterns that occur over time and present this information in a manner that is both valuable and easily understandable. To do that we are building the best computer vision team in the world for large scale automated analysis of satellite and aerial imagery.

To support this work, we need creative and expert researchers who are not afraid of tackling new computer vision problems. Our scientists and engineers have a true passion for data and a commitment to build for today and invent for tomorrow. We are actively engaged with the AI research community, frequently attending both local talks and global conferences and encouraging team members to publish their work. If you join us, you'll have the freedom to approach, own, and solve problems creatively.

The world is a very big place. With a single photograph of Earth, like the famous "Blue Marble" from Apollo 17, the entire world can fit on a computer screen. However, with this image you would not be able to see much detail. To see the Earth and all of its rich features, you would need a lot more images. In fact, it would take over 500 million images just to observe the land area of Earth at 1 meter pixel resolution.

In order to see detail and work at this scale, we use computer vision and machine learning. Using convolutional neural networks, we have counted over 3 billion cars across global roads and parking lots, analyzing commercial patterns as well as city growth and development. Our global energy product uses computer vision to map floating roof oil tanks and measure the global volumes of crude oil. With this product, we were able to show that China has 200 million barrels of oil storage capacity that was unknown even to the trading community. Other projects include tracking rates of deforestation, measuring poverty levels around the globe, monitoring construction rates of new roads and buildings, and predicting crop yields. This is still the beginning of our mission to understand the Earth.

Job Duties

  • Develop highly scalable machine learning and computer vision models for processing large quantities of high-resolution satellite imagery and other remote sensing data

  • Rapidly iterate algorithms to improve performance and generalization to new data

  • Engage in fundamental research in relevant areas of machine learning and computer vision, such as semi-supervised, unsupervised, transfer and active learning.

  • Stay current on the latest ML/CV research by reviewing papers and implementing state-of-the-art concepts

  • Work cross-functionally with data ops and core engineers to establish data requirements and metrics for computer vision algorithms

  • Implement and test software utilities for internal computer vision research as well as deploying computer vision models as part of the product

  • Collaborate with end-user product owners to understand computer vision needs

  • Support build deployment, management, and monitoring systems

Skills & Qualifications (required)

  • Academic degree (BS required, MS and PhD preferred) in computer science or other quantitative discipline

  • Demonstrated ability to create, invent, and innovate

  • Solid understanding of current deep learning-based computer vision techniques

  • Ability to work both independently and collaboratively in a fast-paced research environment

  • Ability to effectively communicate results and ideas via presentations and technical reports

  • Solid programming skills in Python and strong algorithmic thinking

Skills & Qualifications (preferred)

  • Strong background in statistical machine learning

  • Understanding of statistical inference (e.g., Bayesian modeling, MCMC)

  • Experience working with remote sensing data such as EO, SAR, Hyperspectral, or Lidar

  • Understanding of fundamental concepts of signal/image processing: Fourier techniques, filtering, etc.

  • World-class foosball skills

We are backed by marquee investors such as Sequoia Capital, Google Ventures, In-Q-Tel, and Bloomberg Beta, Orbital Insight is rapidly expanding its commercial and public sector capabilities. Come join us if you are unafraid to try new approaches and relentlessly seek to push the state of the art, taking projects all the way from prototype to production-ready.


Stock Options

Competitive Salaries

Paid time off

Medical, dental, and vision insurance

Life & disability coverage

Flexible Spending Accounts

Apple equipment

Weekly catered lunches

Weekly happy hour in office

Stocked kitchen with healthy snacks, coffee, tea, etc.

MBTA commuter benefits

Note to Recruiters and Placement Agencies: Orbital Insight does not accept unsolicited agency resumes. Please do not forward resumes to any person or email address at Orbital Insight prior to obtaining a signed agreement from Recruiting/HR. Orbital Insight is not liable for and will not pay placement fees for candidates submitted by any agency other than its approved recruitment partners. Furthermore, any resumes sent without an agreement in place will be considered your company's gift to Orbital Insight and may be forwarded to our recruiters for their attention.

See if you are a match!

See how well your resume matches up to this job - upload your resume now.

Find your dream job anywhere
with the LiveCareer app.
Download the
LiveCareer app and find
your dream job anywhere

Boost your job search productivity with our
free Chrome Extension!

lc_apply_tool GET EXTENSION

Similar Jobs

Want to see jobs matched to your resume? Upload One Now! Remove
Research Scientist Computer Vision (Phd University Grad) 2019


Posted 1 week ago

VIEW JOBS 11/5/2018 12:00:00 AM 2019-02-03T00:00 We are seeking world-class computer vision experts to join our teams in developing next generation products and platforms doing research and engineering at scale. We're applying cutting-edge computer vision algorithms to a wide range of media understanding challenges at Facebook. RESPONSIBILITIES * Develop novel and accurate computer vision algorithms and systems, leveraging deep learning and machine learning on big data resources. Analyze and improve efficiency, scalability, and stability of various deployed systems. Collaborate with team members from the level of prototyping to the level of production. MINIMUM QUALIFICATIONS * Currently has or is in the process of obtaining a PhD degree or completing a postdoctoral assignment in the field of Computer Vision or similar Must be available to start employment on or after January 1, 2019 Interpersonal experience: cross-group and cross-culture collaboration Research and/or work experience in machine learning, deep learning, and/or computer vision Experience in C/C++ Proven track record of achieving results as demonstrated by grants, fellowships, patents, as well as first-authored publications at workshops or conferences such as CVPR, ECCV, ICCV, SIGGRAPH or similar PREFERRED QUALIFICATIONS * Experience developing novel algorithms in the following: * Deep adversarial networks, image and video forensics. * Cross domain adaptation for rapid model transfer across domains. * Transfer learning including zero shot learning, attribute learning, and knowledge graphs. * Deep graphical modeling. * Explainability in computer vision and AI such as image and video captioning, and causal reasoning. Experienced with the development of enterprise level AI, machine learning and deep learning platform involving big data management and GPU compute. Experienced with training deep neural networks for key computer vision tasks such as classification, semantic segmentation, object detection, etc. Experience in mobile Augmented Reality systems and shipping a major mobile app. Facebook Boston MA

Computer Vision Scientist

Orbital Insight