The latest opportunities from ecm.

See what we can offer you, and tell us you're interested. We'll do the rest.

The ecm guarantee.

We know what it's like to be looking for a high-tech job - we've worked in the industry ourselves! Here's how we work:

  • If you send your details to ecm, we treat them as confidential.
  • We only send your CV to a company with your express prior permission.
  • We will speak to you before we do anything.
  • All ecm consultants have a technical background in engineering, maths or the physical sciences.
  • Let us do the hard work – if you can't see quite the right job for you, let us look for you.

Researcher - Machine Learning/Motion Prediction (23498)

Edinburgh
£Outstanding + shares

Top qualifications, Behaviour modelling, Bayesian methods, Optimisation

Researcher - Machine Learning / Motion Prediction
Top qualifications, Behaviour modelling, Bayesian methods, Optimisation
Edinburgh
£Outstanding + shares (likely to be over £70k for the right experience)

Can you offer an outstanding academic record in Machine Learning as applied to Prediction / Behaviour modelling / Bayesian methods / Large-scale optimization / Probabilistic inference or similar?

This is a very rare opportunity to join a renowned and highly respected company working on leading edge research encompassing Deep / Machine Learning, Artificial Intelligence, Neural Networks, Planning Systems, Robotics and 3D Mapping.

You will earn an outstanding salary - but also acquire start-up stock options in a future global leader!

Only the best need apply: These exciting roles call for exceptionally bright researchers who are self-starting high-achievers – with very strong mathematics skills and proven coding fluency (for example C / C++, Python, Scala, MATLAB, Java). You should of course also have an outstanding academic background (PhD / Masters from a top University & publications in top scientific journals) plus proven postgrad / industrial research experience, along with the drive and ambition to rapidly advance your career.

The role calls for:

  • Strong background in machine learning as applied to prediction, action, behaviour, autonomous and lifelong agent learning, Bayesian methods in decision making etc
  • Strong analytical background and deep understanding of large-scale optimization, numerical linear algebra, probabilistic inference
  • Strong programming skills (eg Python, C/C++, Scala, Matlab, Java) as well as LINUX, HTML and GPU programming including CUDA
  • Excellent communication skills (fluency in English essential)
  • Desire to work in a fast-paced start-up environment
    Your responsibilities will include:
  • Research and then develop state-of-the-art large scale predictive models of dynamic road scene environments to produce rich predictions, dynamic cost maps and motion plans
  • Explore and develop richly-structured end-to-end deep neural networks to provide intermediation between perception inputs and useful outputs, such as dynamic cost maps
  • Apply novel prediction techniques such as inverse reinforcement learning (inverse optimal control) to generate those cost maps; find novel ways of using vast quantities of un-annotated video footage to learn those cost functions
  • Develop and improve ways of establishing beliefs in the goals and behaviours of actors in road scenes and develop and curate learnt behavioural model libraries
  • Research and identify suitable methods of building memory into these models, for example using LSTMs and RNNs
  • Research novel means of natively modelling interactive and dynamic motions using those beliefs, dynamic costmaps and kinematic models of each actor, such as dynamic programming-based solvers
  • Explore and implement game theoretic approaches alongside reinforcement learning to predict interactive actor behaviour in road scenes and their likelihoods
  • Find ways of using deep perception outputs to improve those predictions (gestures, pose, gaze, wheel movements etc) and identify means of feeding those requirements back to the perception layers of the run-time vehicle stack
  • Select and develop path planning methodologies, likely based on variants of D*, A*, RRT* algorithms, which, together with kino-dynamic vehicle models, deliver feasible and preferred paths
  • Generate novel research techniques for solving multiple challenges in the field of computer vision as applied to autonomous vehicles and work to get outputs published in the world’s top scientific journals and conferences

As the team grows, you will find yourself quickly surrounded by subject matter experts in one of the most exciting technology domains and will rapidly gain knowledge and experience.

Please note: even if you don’t have exactly the background indicated, do contact us now if this type of job is of interest – we may well have similar opportunities that you would be suited to. And of course, we always get your permission before submitting your CV to a company.