Computer Vision Engineer Lead

We are looking to add a talented and motivated individual to become the lead of our user tracking/computer vision team at Audioscenic Limited. If you are passionate about making practical products, have a good knowledge of user tracking technologies, know how to work in a team and inspire others, and want to help us change the way that people consume Spatial audio - this is your role!


Job Description

The Audioscenic listener-adaptive 3D audio technology uses computer vision to track and deliver audio beams directly to the users’ ears in real time. This allows a super immersive spatial audio experience without the need of wearables or headphones. An example of a system using our technology can be found here:

We are looking for a skilled computer vision engineer that can help us improve and further develop our computer-vision system. The aim is to take our head-tracking software to the next level and help us become a world leader in advanced 3D audio reproduction systems. 

For this, we are looking for an experienced individual that understands well the state of the art of user tracking and computer vision, and that can help us tailor existing algorithms and develop new ones to obtain a suitable user tracking needed for deploying our technology. 


We are looking for an individual that is practical, can understand the different blocks and processes needed to achieve a tracking goal and that also understands what is needed to implement this in an embedded device.


The candidate should have experience maintaining code and documentation to high quality standards and very important, to work with a multidisciplinary team, formed of both other computer vision engineers and of our wider audio team. 


The successful candidates will work with our multidisciplinary team to develop working versions of systems using RGB cameras and depth sensors, building single and multi-listener tracking, and pose estimation applications for PCs and embedded systems.


The technology developed at Audioscenic is aimed at novel consumer products that will represent the forefront of audio engineering in the years to come. Working with us you will have the opportunity to work with customers all over the world.


Audioscenic is a young VC backed start up, offering the benefits of a friendly working environment and a wide range of day-to-day tasks with opportunities for training, career progression and international travel.


Lab-based work is required for the tuning and development of systems, but a flexible lab and home-work basis is possible when convenient.



Degree or PhD in Computer Science, electronic engineering, or equivalent experience.

Previous experience

Preferably 2 or 3 years in enterprise or research computer vision and head tracking engineering roles.


Skillset and Interests


  • Understanding of computer vision techniques and methods

  • Experience in developing computer vision software

  • Experience with OpenCV

  • Proven programming skills in C++ and Python

  • Experience in designing and training vision models

  • Experience in combining models and techniques to achieve high level goals using computer vision.

  • Experience with different camera and sensor technologies (RGB-D, Infrared, etc.) and specifying camera requirements 

  • Experience with testing and evaluating computer vision systems

  • Experience of additional computer vision frameworks is desirable

  • Experience of DNN optimisation is desirable

  • Experience developing user tracking or other object localisation vision systems is desirable

  • Experience with LIDAR / other user-tracking systems is desirable

  • Experience of combining computer vision with other sensing technologies  is desirable

  • Audio interests are a plus

  • Strong communication skills and friendly personality are a plus plus


To apply please email your CV to


Southampton, UK