Open position: ML, Vision

Developer in Computer Vision and Machine Learning Research

Salary:Not specified
Hours:Full Time
Contract Type:Fixed-Term/Contract

We are looking for an R&D developer for an initial 24 month (extension possible).

The role will be to research, develop and deploy AI image recognition software within a Euro 6 m funded EU project (13 other partners in Europe and one in South America) from 1 Nov 2019. The project aims to integrate Citizen Science in the European Open Science Cloud. The main focus of this position will be on software to automatically assess, eg, camera trap images using machine learning as to whether or not they show interesting animals (or are false alarms, say, owing to wind) and, if so, which species that is.

There is substantial scope for exploring your own ideas within this project. Also, you will be interacting with some of the world-leading research teams in this space of monitoring biodiversity. The role will develop a service for the automatic pre-processing of video streams (or regular snapshots) coming from diverse devices that might be used in citizen science projects (e.g. mobile phones, camera-traps, personal drones, etc).

Processing goals include:
(1) compression of data and filtering (noise, lighting/weather filters, other useful optical filters);
(2) preparation for deep learning processing — lower resolution, available labelling (time, weather index, temperature, location), sub-sampling (in time, adaptive to movement or change detection);
(3) on-board processing: mainly applying Deep Learning (DL) techniques made available through other services;
(4) preparation of results and archiving or delivery on the cloud.

The role will specifically look at the service required to process observations from camera traps which get continuous flows of images or videos to process. The service to develop should be able to: (1) automatically filter most (if not all) of the unwanted pictures, and (2) propose the species most likely name(s). The idea is to create a GUI that utilises our research results (within the consortium), that allows users to visualise results, and, if they accept the suggested classification, the picture is uploaded to any of the chosen biodiversity platforms with the proposed identification.

DynAIkon are also involved in other parts of the project which means that it is likely there will be some travel to/from Spain, France, Greece, The Netherlands, Germany, Columbia, Sweden, besides the UK. Some details available here: Co-designed Citizen Observatories Services for the EOS-Cloud (H2020)

If you would like to discuss the particulars of this role before making an application, please contact Prof Frederic Fol Leymarie (

Key Responsibilities:
• Conduct research into automated image recognition for biological species recognition from images, videos.
• Co-create (with other interdisciplinary researchers and end users) interfaces to effectively use image recognition in citizen science projects.
• Integrate software to work with major nature observation platforms such as:, Natusfera, Pl@ntNet or Artportalen.
• Help write and publish findings in internationally leading conferences and journals.

Skills and Experience:
We are looking for candidates with:
• A PhD (or equivalent level with demonstrable portfolio) in topics related to Artificial Intelligence, Machine Learning, Computer VIsion, and, ideally, also Human Computer Interaction or Citizen Science.
• Experience with Artificial Neural Networks, and ability to design these  for bespoke image classification.
• Strong programming skills, and some interest in web development and design.
• Interest in Citizen Science, preferably in the biodiversity monitoring domain.
• Ability to work in a team and communicate across research sites.
• Strong record of scientific publication commensurate with experience.

Research Environment

DynAIkon Ltd is a start-up co-funded by two researchers, Prof. Stefan Rueger and Prof. Frederic Fol Leymarie, with the aim to further develop and bring to production real life applications, by incoporating recent advances made in computing at the intersection of: computer vision, AI and ML, information retrieval, with a current focus on biodiversity monitoring.

Contact us :