Modelling Engineer

Website Luffy AI

Next generation AI for robotics and industrial control

The Role

We are looking for a passionate Modelling Engineer that can sit in our AI & Software team developing robust simulation models for training AI controllers. Our potential customers span a range of robotics and industrial process companies. When training AI networks for these applications, we require digital twin models that expose the networks to the full range of system dynamics and phenomena encountered. These digital twin models are typically derived from a range of in house physics engines, which are configured for the application under development. In this role you will be both maintaining our existing physics engines and developing new models for future markets.

This dynamic role will require you to have a broad interest in disciplines such as AI technologies, software engineering, chemical/industrial processes, mechanical and electrical engineering, and robotics. The code frameworks you will work on include multi-physics simulators and specialised engineering process models. Ideally, you will have strong software engineering skills and experience in working in a research environment. You will be able to work with a high degree of autonomy, seeking out expertise and advice from domain experts as required. You care deeply about software standards and enjoy working on challenging research problems, sometimes requiring experimentation. Examples of excellent practical experience include working with multiphysics research codes (both research and commercial e.g. COMSOL), industrial process modelling tools, game engines (graphics, physics) and autonomous mobile robots (perception, controls).

Roles and Responsibilities

  • Mathematical modelling of high performing dynamic systems (including sub system components and system environment). Developing our core physics engines and reference industrial process models.
  • Refactoring existing frameworks to achieve optimum performance.
  • Model design, implementation, testing, code reviews and preparation of supporting documentation.
  • Implementing digital twin models as required for specific customer applications, benchmarking these models against experimental data.
  • Interacting with customers to capture all the physics and control characteristics of the system being controlled, developing requirements for the digital twins.
  • Assisting the AI team with digital twin development, system integration and field testing. Ensuring the models are fit for the intended uses.
  • Developing visualisation tools for digital twins and physics engines, alongside other developers.
  • Performing research into problem areas to advance knowledge, evaluate new approximations and numerical techniques, estimating the range of validity of models.
  • Qualifications and experience.

Essentials we’d like you to have:

  • University degree in a relevant area of engineering/science (physics, maths, chemical engineering, mechanical engineering) or an equivalent qualification. An advanced degree may be an advantage but is not required.
  • 5+ years of relevant experience in science/engineering disciplines. Significant experience of developing modelling codes for dynamic multi-physics systems.
  • Strong understanding of the numerical algorithms related to physics codes, e.g. finite element methods, statistical sampling, numerical integration schemes.
  • Strong mathematical skills (degree level).
  • Strong programming skills in the Python and C/C++ programming languages.
  • Skilled with software architecture and advanced programming techniques.
  • Ability to produce visualisation tools that support scientific codes (graphing and 3D visualisations, Python/JS).
  • Must be able to autonomously research and learn about new systems/processes. Be able to make and justify approximations relevant to the simulation fidelity required.
  • Good understanding of code profiling, performance and numerical optimisation techniques.
  • Strong familiarity with testing frameworks and continuous integration.
  • A desire to help other people solve their problems.
  • Excellent communication skills.

Bonus points will be awarded for:

  • Familiarity/interest in industrial process simulation tools. Relevant sectors include but not limited to: aerospace, oil & gas, cement, steel, glass, mining, chemical processing.
  • Interest in theoretical and numerical aerodynamics.
  • Experience with commercially available multi-physics codes (e.g. COMSOL).
  • GPU programming (CUDA).
  • Knowledge of three.js or equivalent 3D visualisation libraries.
  • Comfortable reading research codes in Matlab & Fortran.


  • Salary in the region of £40k – £60k pa depending on experience and capability assessment during the interview process.
  • EMI share options scheme
  • 25 days annual leave, plus bank holidays
  • Flexible working – we require a minimum level of on-site presence, but will accommodate your work style preferences where possible. We can’t accept fully remote candidates.

More About Luffy AI

We are an exciting high-tech startup developing adaptive neural networks for industrial control. Luffy specialises in adaptive AI controllers that can be trained in simulation on digital twins and successfully transferred into real world systems. Our networks use neural plasticity to learn the dynamics of the equipment they are placed in and continue to adapt long after training. These innovations allow us to over come the problems of using Machine Learning in control system applications.

Our first customer is an advanced injection moulding process used in Automotive and Aerospace. The AI will replace conventional PID controllers, improving the energy efficiency, yield and product quality. This revolutionary control technology can have an impact in Industry 4.0 manufacturing and foundation industries such as Steel, Glass and Cement manufacturing. It can also be applied to robotic systems such as drones.


Applications close by Monday 17th of October. May close earlier if sufficient applications are received. Please apply through the LinkedIn advert.

To apply for this job please visit

About the author: matthew.carr