Simulation Engineer Autonomous & Soft Robotic Systems in London

Your mission is to build simulation tools for soft and hybrid robotic systems, focusing on physically realistic modeling that supports fast, reliable iteration from concept to evaluation. You will help develop the simulation capabilities and software interfaces that make these models useful in practical engineering workflows.

Your Role involves owning the physical simulation stack used to model 3D geometry, material behaviour, deformation, and dynamics of soft and hybrid robotic systems. You will be responsible for model fidelity, computational performance, validation/calibration against real-world measurements, and for delivering simulation outputs in forms that other systems can consume. You will work closely with colleagues across adjacent technical areas while owning the simulation architecture and its evolution.

Primary focus areas include:

• Running high-fidelity physical simulations of soft and hybrid robotic systems, capturing 3D shape, material behaviour, deformation, and dynamics.
• Simulation-in-the-loop workflows, where physical simulation outputs guide design-space exploration and decision-making.
• Validation and automated calibration against experimental data to reduce the simulation-to-reality gap.

Your profile includes:

• Design, implement, and run physics-based simulations for soft and hybrid robotic systems, including large deformation, nonlinear materials, and relevant contact or fluid/structure interaction effects (as needed).
• Develop finite-element and/or reduced-order models that expose physically meaningful outputs (e.g., deformation fields, stresses, energies, performance metrics) for use in optimization workflows.
• Translate simulation results into structured signals suitable for automated design and optimization.

• Integrate physical simulation into optimization and learning-driven workflows, where simulation outputs inform design decisions and parameter updates.
• Support simulation-in-the-loop experimentation for autonomous discovery, calibration, and iterative refinement.
• Define robust data interfaces between simulation and other components (schemas, metadata, versioning, traceability).

• Optimize simulation performance to balance physical fidelity and computational efficiency in iterative workflows.
• Implement adaptive meshing, model reduction, or surrogate modeling strategies where required for scalable exploration.
• Support batch and high-throughput simulation workflows for large-scale design-space evaluation.

• Design validation protocols comparing simulation predictions to experimental measurements.
• Develop automated calibration and parameter-estimation routines to align simulated behaviour with real-world response.
• Quantify uncertainty, sensitivity, and known limitations of simulation models used in decision-making.

• Build clean, well-documented simulation-facing APIs that expose physical simulation results to optimization and experimentation systems.
• Implement data logging, versioning, and reproducibility practices for simulation-driven experiments.
• Contribute to shared infrastructure using modern version control and CI practices.

Qualifications

Required:

• Master’s degree or PhD in Mechanical Engineering, Robotics, Computational Mechanics, Physics, or a closely related field.
• Strong background in computational mechanics, finite element methods, and numerical simulation.
• Hands-on experience with physics simulation tools (e.g., Abaqus, ANSYS, COMSOL, or equivalent).
• Proficiency in Python and C++ for scientific and simulation software development.
• Experience with mesh generation/refinement and numerical stability issues.
• Solid foundation in continuum mechanics, nonlinear materials, and numerical methods.
• Experience working in collaborative, research-driven engineering environments.

Preferred:

• Experience with soft robotics or compliant/hybrid robotic systems.
• Familiarity with modern physics engines or robotics simulation platforms (e.g., NVIDIA Omniverse/PhysX, Isaac Sim, MuJoCo, PyBullet).
• Experience integrating physical simulation outputs into optimization or learning-based pipelines (e.g., Bayesian optimization, evolutionary algorithms, active learning).
• Exposure to experimental validation or automated testing workflows.
• Experience with visualization tools such as ParaView, VTK, PyVista, vedo, or Blender.
• CI/CD experience for simulation or scientific software.

Why us?

• Competitive salary and benefits package.
• Opportunity to help define foundational technology at a stealth startup at the forefront of robotics.
• Significant scope for growth and leadership as part of the early team.
• Collaborative, mission-driven culture.
• Visa sponsorship for candidates.