[ES_JOBS_NET] Machine Learning Engineer - Remote Sensing at Global Fishing Watch

Fri Jan 12 14:46:07 MST 2024

*Background:* Global Fishing Watch is an international, non-profit
organization committed to advancing ocean governance through increased
transparency. We create and publicly share knowledge about human activity
at sea to enable fair and sustainable use of our ocean. Founded in 2015
through a collaboration between Oceana, SkyTruth, and Google, GFW became an
independent non-profit organization in 2017. Using cutting-edge technology,
we create and publicly share map visualizations, data and analysis tools to
enable scientific research and drive a transformation in how we manage our
ocean. By 2030, we aim to monitor and map all commercial activity at sea,
including all industrial fishing vessels, small-scale fishing activity, all
large non-fishing vessels, and all fixed infrastructure such as aquaculture
and oil rigs. We also plan to work with intergovernmental organizations and
30 governments around the globe to promote the adoption of transparency
more widely and publicly share ocean data to drive better management of
marine resources.

*The Position*

The Research and Innovation team at Global Fishing Watch (GFW) connects
data science and machine learning experts with the scientific community to
produce new datasets, publish impactful research, and empower others to use
our data. This team harnesses satellite technology, machine learning, and
big data to shed light on some of the most pressing issues facing the ocean.

We are now working to map the global footprint of commercial activity at
sea, including the activity of all ocean-going vessels and fixed
infrastructure. This work involves combining deep learning and data fusion
techniques with petabytes of satellite imagery (radar and optical), and
billions of GPS positions from vessels, mostly from the Automatic
Identification System (AIS) and Vessel Monitoring Systems.

The Machine Learning Engineer will assist with large data pipelines of
satellite imagery and help build computer vision models to detect and
classify maritime objects in imagery data. The initial focus will be on
vessel detection in high-resolution (3 m) PlanetScope optical imagery from
Planet Labs, leveraging an existing model architecture developed for
Sentinel-2. Subsequent work includes implementing new models to expand the
detection capability to offshore infrastructure using new satellite imagery
sources. The candidate will also collaborate closely with other members of
the Research and Innovation team to correlate detected vessels (position,
time and length) to vessels tracked by AIS. Finally, the candidate will
work closely with the GFW Engineering and Product teams to ensure solutions
are compatible and scalable within our cloud infrastructure.

The incumbent will gain experience working with leading researchers in the
field and will interface daily with GFW’s team of data scientists and
machine learning experts. They will develop further technical skills in
programming, big data, and cloud computing while working for a globally
diverse and fully distributed organization. The successful candidate will
be organized and excited to help Global Fishing Watch develop strong
partnerships and cutting-edge research.

*Principal Duties and Responsibilities*

Model development for small object detection

   - Design, train, and evaluate computer vision models for object
   detection in satellite imagery, with an emphasis on vessel detection in
   optical imagery
   - Implement preprocessing pipelines to obtain imagery and prepare it for
   annotation and modelling
   - Devise annotation strategies and tools for labelling vessels and fixed
   infrastructure in satellite images
   - Improve our training datasets and build new training datasets for
   other human-made objects, potentially managing external annotation services

Additional tasks may include

   - Provide technical support to the senior machine learning engineer(s)
   responsible for developing and advancing other Global Fishing Watch models
   - Assist data fusion efforts to integrate detections from multiple
   sources (e.g. Sentinel-1 SAR and Sentinel-2 optical), accounting for the
   recall of each model, length of the objects, cloudiness, and image
   resolution, among others
   - Analyze large amounts of data from various sources, such as vessel
   tracking, identity, and satellite imagery to identify trends, anomalies,
   and insights
   - Ensure the integrity and accuracy of key data pipelines and research
   BigQuery tables
   - Maintain and improve internal Python tools, such as modules and
   template repositories, to assist with migrating research projects from
   proof-of-concepts to automated prototypes
   - Lead or support eventual research publications and technical blog posts

*Candidate description*

*Skills you should have*

   - Bachelor's degree and at least four years of professional experience,
   or an equivalent combination of education and experience, in physical/earth
   sciences or a related field
   - Demonstrated skills and experience with Python
   - Strong foundation in mathematics and statistics
   - Familiarity working with geospatial data
   - Demonstrated experience working with cloud compute platforms and
   virtualized environments
   - Self-motivated with a strong curiosity and desire to learn new skills
   - Willingness to take ownership of projects and communicate project
   updates
   - Written and verbal communication skills in English
   - Ability to work with a remote team and embrace Slack, Google Suite,
   Jira, Notion and other collaborative tools

*Also great*

   - Some experience with database query languages such as SQL
   - Demonstrated experience with computer vision models
   - Demonstrated experience with frameworks such as TensorFlow or PyTorch
   - Familiarity with containerization tools like Docker and execution of
   models inside them
   - An appreciation for the complexities and rewards of collaborating in a
   remote, global and inclusive environment
   - Experience engaging with academic researchers and the peer-review
   process
   - Awareness of ethical considerations related to privacy and bias in
   satellite imagery analysis

The successful candidate will meet most, but not necessarily all, of the
criteria above. Although it is obviously helpful, we do not expect that you
already have a deep knowledge of building models or our key programming
languages; we do expect that you have the aptitude to develop these skills
and knowledge, and that you are excited about revealing human activity
across the global ocean using these tools. If you don’t think you check all
the boxes, but believe you have unique skills that make you a great fit for
the role, we want to hear from you!

*To Apply:* Please submit the application at
https://boards.greenhouse.io/globalfishingwatch/jobs/5842515003

*Please apply by January 26, 2024*

*Additional Information*

Reporting to: Senior Data Scientist / Senior Data Science Manager

Manages: NA

Location: Remote - we welcome candidates based in any country

Term: Permanent position

FT/PT: Full-time

*Recruiting process*

A cover letter along with a CV will be requested to see how your experience
and interest connect to the position. We expect the cover letter to explain
details on how your skills, interests, and aspirations align with the role.
If selected for consideration, the hiring process for this position will
include a formal 45 minute interview with 2-3 staff followed by a 30 minute
administrative screening by a Human Resources manager. Candidates advancing
beyond this round will be asked to take a technical assessment. Lastly, an
informal 30 minute call with 3-4 members of the Research and Innovation
team will be held with finalists.

*Please apply by January 26, 2024*

*Working Hours:** Global Fishing Watch supports flexible working, so the
pattern of hours may vary according to operational and personal needs. The
position will be part of a global team spanning many different time zones
and so the candidate should be able to accommodate semi-regular early/late
meetings to be able to work effectively. Weekend work may be required on
occasion. The post holder may be required to undertake regional and
international travel. No overtime is payable.*

*Compensation:** A compensation range for this position is **US$
90,000-$110,000 **for US-based employees - For applicants located outside
of the US, the pay range will be adjusted to the country of hire**.**
Compensation
is commensurate with experience and will vary depending on the hired
candidate’s country of residence, in accordance with local laws and
regulations. GFW offers pension/retirement, health and other benefits
commensurate with similar level GFW employees in the country of employment.
The position may be a GFW employee or consultant, depending on the country
of residence  *

*Equal opportunities**: Global Fishing Watch is an equal opportunities
employer. Global Fishing Watch is committed to promoting diversity and
inclusion within our organization and in the greater ocean management and
conservation community. We believe that diverse backgrounds, skills,
knowledge, and viewpoints make us a stronger organization. Bringing
together professionals who possess broad experiences and a spectrum of
perspectives will enable us to reach our goal of improved ocean governance
faster. We hire and promote qualified professionals without regard to
actual or perceived race, color, religion or belief, sex, sexual
orientation, gender identity, marital, or parental status, national origin,
age, physical or mental disability or medical condition, or any other
characteristic protected by applicable law. Our organizational goals match
the urgent challenges facing our global ocean, and our mission is designed
to help secure a healthy ocean for all. We are committed to building a
workforce that is representative of humanity’s diversity, by providing an
inclusive and welcoming environment for all employees of Global Fishing
Watch and for our partners, vendors, suppliers, and contractors.*

-- 
*Zihan Wei* (He/him/his)
*Data Scientist (Geospatial), Research and Innovation*
------------------------------
Web globalfishingwatch.org
Email zihan.wei at globalfishingwatch.org
<https://www.linkedin.com/company/global-fishing-watch>
<https://twitter.com/GlobalFishWatch>
<https://www.youtube.com/globalfishingwatch>
<https://www.facebook.com/GlobalFishingWatch>
<https://www.instagram.com/globalfishingwatch/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.ucar.edu/pipermail/es_jobs_net/attachments/20240112/c8face4c/attachment-0001.htm>