Senior AI Engineer , Physics AI
Firmus Technologies3 hours ago
Singapore, SingaporeSenior
Responsibilities
- Develop and qualify surrogate models for bounded thermal, airflow, cooling, and infrastructure scenarios.
- Build reproducible pipelines from Ansys Fluent and other engineering tools into model-ready datasets while preserving geometry, mesh, equipment, boundary-condition, unit, and solver-version lineage.
- Deliver tested and versioned production software, including training pipelines, model registries, inference APIs, qualification workflows, model packaging, monitoring, and documentation.
- Deploy surrogate-model endpoints through the AI and Applications inference platform and integrate them with GPU scheduling, engineering optimisation, evidence-linked design records, and visualisation services.
- Define model acceptance criteria and evaluate accuracy, local errors, physical consistency, latency, uncertainty, applicability domains, and performance against simpler baselines.
- Implement out-of-distribution detection, rejection or solver-fallback behaviour, traceability, and safe shadow-mode operational evaluation.
- Integrate surrogate models into scenario screening, design comparisons, commissioning rehearsal, operating-envelope studies, and whole-factory decision support.
- Technically lead cross-disciplinary work across ML, simulation, software delivery, and engineering teams while setting standards, reviewing designs, and mentoring engineers.
Requirements
- Deep hands-on experience in scientific machine learning, computational engineering, or simulation-led software, with evidence of taking models from research into dependable production services across multiple projects.
- Technical leadership of at least one cross-disciplinary programme spanning machine learning, simulation, and software delivery.
- Strong Python and PyTorch skills, including developing, training, profiling, evaluating, and deploying models on GPU infrastructure.
- Experience with surrogate modelling, neural operators, graph neural networks, reduced-order modelling, physics-informed learning, or closely related methods.
- Working knowledge of simulation data, meshes, geometry, boundary conditions, numerical validation, discretisation, convergence, conservation, data coverage, and measurement uncertainty.
- Ability to distinguish interpolation from unsupported extrapolation and determine when a surrogate should defer to an authoritative engineering calculation.
- Experience building maintainable software with APIs, containers, version control, automated tests, CI/CD, and observability.
- Ability to design reproducible data and model contracts, diagnose failure modes, and collaborate across engineering disciplines.
- A degree in engineering, computer science, applied mathematics, computational physics, or a related discipline, or equivalent practical depth.
- Preferred experience with NVIDIA PhysicsNeMo or Modulus, PyTorch Geometric, graph or operator learning, uncertainty quantification, and multi-GPU training.
- Familiarity with Ansys Fluent or PyFluent, OpenFOAM, ETAP, CAD-to-simulation workflows, OpenUSD, Omniverse, Kubernetes, or on-premises accelerated computing is valuable.
- Experience with data-centre thermal systems, liquid cooling, electrical infrastructure, or GPU/HPC environments is useful.
Benefits
- Permanent, full-time employment.
- Role based in Singapore or Sydney, working closely with Engineering and Technology and Operations.
- Opportunity to work with founders and experts in AI infrastructure, energy systems, and next-generation compute.
- Direct ownership and exposure across a founder-led, rapidly scaling AI infrastructure company.
- Inclusive workplace encouraging applications from candidates of all backgrounds.
Tech Stack
Categories
About Firmus Technologies
Firmus Technologies builds energy‑efficient AI infrastructure, developing liquid‑cooled “AI Factory” data centers and operating a large‑scale GPU cloud for model training. The company sells capacity and services to developers, enterprises, education, and government customers, with a focus on energy and cost efficiency across Asia‑Pacific. Founded in 2019 in Australia, Firmus is privately held and headquartered in St Leonards, Tasmania.