The opportunity:
Our algorithms are central to the design of sophisticated guided weapon systems products. These algorithms are developed throughout the lifecycle of the product and include research studies for future developments.
Intelligent Autonomous Systems (IAS) Engineers are involved in project lifecycles, playing a pivotal role in our product development, including:
- Technical development of specific algorithms or studies for key programmes, including feasibility studies, algorithm design and trade-off studies, trial preparations, analysis and reporting, architecture definition, validation of algorithms and models.
- Technical assessments and investigations into various issues, developing solutions either independently or as part of a team.
- Engaging with algorithm users to understand and respond to their needs, ensuring algorithms are fit for purpose.
What we’re looking for from you:
- Degree/PhD in a related field or a degree with mathematical content and programming skills.
- Relevant experience (post-doctoral or industrial) in robotics, data fusion, tracking/estimation, pattern discovery & recognition, statistical inference, optimisation, and machine/deep learning algorithms, including real-time implementation and validation & verification.
- Experience with Matlab, Simulink, Stateflow, Python, PyTorch, TensorFlow, OpenAI-Gym/Universe, or Model-Based Design is desirable.
Engineers are encouraged to develop broad and in-depth knowledge across various fields, with specific knowledge or experience in the following areas being beneficial:
- Robotics, guidance, and autonomous decision-making: routing, motion/trajectory planning, optimisation, guidance and control, decision theory, MDPs/POMDPs, game theory, decision support, multi-agent systems.
- Data fusion and state estimation/tracking algorithms: Kalman Filtering, multi-model tracking, particle filters, grid-based estimation, multi-sensor fusion, data association, Bayesian networks, Dempster-Shafer theory.
- Machine Learning: regression, pattern recognition, Gaussian processes, latent variable methods, support vector machines, neural networks, Bayesian inference, random forests, anomaly detection, clustering.
- Deep Learning: reinforcement learning, Monte Carlo tree search, deep regression/classification, embeddings, recurrent networks, NLP.
- Computer Vision algorithms: structure from motion, navigation, SLAM, pose estimation.