TAngraFX

1 Job

1 Employees

About the Company

At TAngraFX, we're revolutionizing the world of VFX by providing cutting-edge multi-physics engines that integrate seamlessly with Blender, with more software compatibility coming soon. Our Software: TAngra - The Multi-Physics Engine for Blender, Maya, 3ds Max: Are you tired of the limitations of traditional VFX tools? Want a solution that supports a range of advanced simulations to bring your vision to life? With TAngra, you get: MPM (Material Point Method) for realistic simulations of granular materials like sand and snow. XPBD (Extended Position-Based Dynamics) for accurate, fast, and stable simulations of soft and rigid bodies. SPH (Smoothed Particle Hydrodynamics) for fluid and particle-based simulations. FLIP (Fluid-Implicit Particle) Splashy, chaotic simulations like crashing waves or pouring water. APIC (Affine Particle-In-Cell) for fluid simulations that capture detailed vorticity. FEM (Finite Element Method) for simulating deformable objects with high accuracy. LBM (Lattice Boltzmann Method) is a mesoscopic fluid simulation technique that models particle collisions and streaming on a lattice grid, ideal for complex flows and highly parallel computing. Granular Solver for detailed interactions in granular materials. No more waiting for hours on end. With TAngra, real-time simulations are at your fingertips, boosting your productivity and creativity. Stay tuned for more software integrations and enhancements! Learn more about TAngraFX and our innovative solutions by visiting tangrafx.com

Listed Jobs

Company Name: TAngraFX
Job Title: HPC AI Developer for Physics Simulation
Job Description: **Job Title** HPC AI Developer for Physics Simulation **Role Summary** Develop, scale, and optimize AI‐driven surrogate models (e.g., Graph Neural Networks, Fourier Neural Operators, Physics‑Informed Neural Networks) for high‑performance physics simulations, delivering production‑ready code on large‑scale supercomputers and GPU clusters. **Expectations** • Deliver end‑to‑end AI model solutions that accelerate or replace conventional physics simulations. • Demonstrate measurable performance improvements and scientific fidelity. • Collaborate cross‑functionally with domain scientists, software engineers, and operations teams. **Key Responsibilities** - Design, implement, and train novel AI/ML models focused on dynamics of physical systems. - Deploy, scale, and optimize models on HPC/GPU clusters using PyTorch (DDP), JAX, or TensorFlow. - Profile and tune AI workloads from single‑GPU kernels (CUDA/Triton) to multi‑node, multi‑GPU training and inference. - Translate physics requirements into computationally efficient, physically consistent models. - Build robust, maintainable scientific software in Python and C++, contributing to core codebases and MLOps pipelines. - Stay current with advances in Scientific Machine Learning, HPC, and AI hardware to continuously improve solutions. **Required Skills** - 3+ years of deep learning model development and training (GNNs, PINNs, operator learning). - Proficient in Python and deep learning frameworks (PyTorch preferred). - Experience with parallel programming and scaling ML on HPC or large‑scale GPU environments (SLURM, MPI, NCCL). - Strong software engineering practices (version control, CI/CD, testing). - Knowledge of performance profiling and optimization (Nsight, VTune). - Familiarity with low‑level GPU programming (CUDA, OpenCL, Triton). **Required Education & Certifications** - M.S. or Ph.D. in Computer Science, Computational Physics, Aerospace Engineering, Applied Mathematics, or related field with emphasis on AI/ML and HPC. ---