P

PhysicsX

Physics AI platform for industrial engineering

CFD Multiphase & DEM Engineer

Thermal & Fluids EngineeringConfirmed live in the last 24 hours
Full-timeSingaporeNo salary listed

About the Job

Requirements

  • Deep expertise in fluid mechanics, heat transfer, and multiphase modelling within bioprocess and chemical engineering environments.
  • High proficiency in at least one of Star-CCM+, OpenFOAM, or Fluent.
  • Experience modelling complex flow behaviour in industrial bioprocess systems.
  • Ability to automate simulation tools to create scalable optimisation workflows.
  • Experience in parametric CAD modelling with NX, CATIA, or equivalent, and coding in Python or ability to quickly learn new programming languages is advantageous.
  • Proficiency in computational fluid dynamics solvers, including custom solver and boundary condition development.
  • Experience with non-Newtonian and complex fluid rheology modelling, including high-viscosity, shear-thinning, or particle-laden flow regimes.
  • Experience with reactive and coupled-physics flow modelling, linking computational fluid dynamics with reaction kinetics, heat transfer, or domain-specific process models.
  • Ability to own meshing generation and strategy for complex industrial geometries, including rotating machinery, internal flow passages, spargers, and free-surface interfaces.
  • Ability to build robust parametric CAD models tightly coupled with simulation pipelines for automated design optimisation and design of experiments studies.
  • Experience developing multi-physics models end-to-end, from geometry clean-up and meshing through solver setup, post-processing, and experimental data integration for model validation.
  • Experience with scale-up/scale-down methodology, translating small-scale experimental data to full-scale computational fluid dynamics models and iterating model fidelity against physical measurements.
  • High-performance computing experience, including job scheduling, MPI-based distributed computing, GPU acceleration, and performance tuning for large-mesh transient simulations on cloud and on-premise resources.
  • Experience with surrogate modelling and machine learning-computational fluid dynamics coupling, including reduced-order or AI surrogate models built from high-fidelity computational fluid dynamics data.
  • Data pipeline literacy, including structuring and curating computational fluid dynamics output datasets for downstream AI/machine learning training, active learning, and Pareto optimisation workflows; applying Latin hypercube sampling, quasi-random, or adaptive sampling techniques to cover design space.
  • Experience with experimental validation workflows, comparing simulation predictions against physical test data, interpreting discrepancies, and improving model fidelity.
  • Ability to communicate results clearly, recommend actionable next steps, and balance accuracy with efficiency under commercial deadlines.

Responsibilities

  • Develop multiphase flow models for gas-liquid and solid-liquid systems using volume of fluid, Euler-Euler, or Euler-Lagrange approaches across industrial and process engineering applications.
  • Model non-Newtonian and complex fluid rheology, including high-viscosity, shear-thinning, or particle-laden flow regimes.
  • Develop reactive and coupled-physics flow models linking computational fluid dynamics with reaction kinetics, heat transfer, or domain-specific process models such as biokinetic, combustion, or electrochemical frameworks.
  • Own meshing generation and strategy for complex industrial geometries, including rotating machinery, internal flow passages, spargers, and free-surface interfaces.
  • Build parametric CAD models coupled with simulation pipelines to enable automated design optimisation and design of experiments studies.
  • Develop multi-physics models end-to-end, including geometry clean-up, meshing, solver setup, post-processing, and experimental data integration for model validation.
  • Apply scale-up/scale-down methodology by translating small-scale experimental data to full-scale computational fluid dynamics models and iterating model fidelity against physical measurements.
  • Use high-performance computing resources, including job scheduling, MPI-based distributed computing, GPU acceleration, and performance tuning for large-mesh transient simulations on cloud and on-premise resources.
  • Build reduced-order or AI surrogate models from high-fidelity computational fluid dynamics data to support design space exploration and process optimisation.
  • Structure and curate computational fluid dynamics output datasets for downstream AI/machine learning training, active learning, and Pareto optimisation workflows; apply data sampling techniques to efficiently cover design space.
  • Compare simulation predictions against physical test data, interpret discrepancies, and systematically improve model fidelity.
  • Partner with clients to scope and address complex engineering challenges through computer-aided engineering and AI solutions, communicate results, recommend actionable next steps, and balance accuracy with efficiency under commercial deadlines.

Desired Qualifications

  • Experience in parametric CAD modelling with NX, CATIA, or equivalent, and coding in Python or ability to quickly learn new programming languages is advantageous.

About the Company

PhysicsX

Physics AI platform for industrial engineering

PhysicsX uses physics-based artificial intelligence for industrial engineering, combining machine learning with physics simulations to shorten design and operation cycles for aerospace, energy, and automotive sectors. Its platform replaces multi-day simulations with near-real-time models that predict performance, helping teams test ideas faster while reducing emissions and costs. It differs from competitors by delivering physics-driven AI with fast, scalable simulations tailored to large, complex industrial systems, supported by a slate of major investors and industrial partners. The company aims to speed up product development and drive broad adoption of physics AI across industrial sectors.

Company size
201-500
Company stage
Series C
Total funding
$487M
Headquarters
London, United Kingdom
Founded
2019

Recently Posted Jobs

Explore more opportunities at PhysicsX

See more jobs