Machine Learning Researcher/ Data Scientist at Predina Tech Limited
London, United Kingdom
🇬🇧 (Posted Feb 11 2019)
About the company
Predina is a funded startup deploying real world Deep Learning and Machine Learning models to predict and prevent the risk of road accidents to save the lives of cyclists, pedestrians and drivers.
We have been rated one of the hottest AI startup in UK by Techworld (https://www.techworld.com/picture-gallery/startups/uk-ai-startups-watch-hottest-machine-learning-startups-in-uk-3645606/) twice in a row (2018 and 2019) and have been endorsed by the UK innovation agency, The Digital Catapult (https://www.digicatapult.org.uk/case-studies/predina/)
You will work directly with the CTO, on the development of our new models in a small tight knit team. We built our first models in collaboration with researchers at the Alan Turing Institute and University of Edinburgh. Currently, our model is able to dynamically predict the likelihood of an accident, the severity of the accident and the potential causes. Our solution is live in vehicles today. The first version of the product is ready and has been validated in the real world.
We have terabytes of data, work with over 10 years of historical accident data (both textual and video) with 28 contextual data variables (including weather, fuel prices, road layout, date, time etc). We also have access to historical accident from 88 countries globally.
Our objective is to build the world’s first dynamic risk map to help people and goods get from A to B safely. Long term application of our technology will be in autonomous vehicles and road infrastructure development.
- Adapt and apply latest development from research to improve the accuracy and granularity of our existing models.
- Identify and apply new and novel datasets to improve the accuracy of existing models and perform predictions at a more granular level.
- Provide feedback on the product direction to extend the existing scope of our solutions.
- Write papers and share your knowledge at leading industry conferences.
- Design and implement creative research solutions to scale out our risk map globally.
- Competitive salary
- Equity package
- We take tremendous pride in the quality of our work.
- We work hard but don't take ourselves too seriously.
- We question traditions and don't do things that are the norm.
***What’s in it for you:***
- Be a part of the core machine learning team building breakthrough technology to save lives globally.
- Bi-weekly team activity
- Free gym
- "Training budget" to help you improve and grow as a professional
Skills & requirements
***Skills and Requirements:***
- PhD or Postdoc in Machine Learning or related disciplines from a top research university.
- Strong publishing track record (ICLR, ICML, NIPS, ICCV, etc) and proven ability to independently produce new research ideas
- Excited to work in a small team and take research ideas into the real world
- Experience using deep learning frameworks (tensorflow or similar)
- Knowledge of python and basic OOP concepts (Desirable)
- 2+ years of experience using deep learning (Desirable)
- 2+ years working in urban informatics (or similar) is a big plus
- Previously worked on road accidents problem is a big plus