Job Requisition ID #
24WD83836
Position Overview
The Simulation, Optimization and Systems (SOS) group within Autodesk Research is seeking an exceptionally talented and experienced Scientific Leader to join our team. We are focused on advancing the state-of-the-art design tools to allow architects, artists, designers, and engineers to “Make Anything”. Our research centers around generative methods for design and spans physics-based modeling, simulation, optimization and systems modeling. You will lead and help build build a group focusing on the future of physics informed AI. Your group will work closely experts in geometric modeling, simulation, systems, robotics, high-performance computing, machine learning, sensing, computer vision, industrial manufacturing and construction.
The Physics Informed AI group will be specifically focused on researching and implementing novel algorithms for physics informed machine learning for use in design and engineering tools. We are interested in a scientific leader to help guide and direct research into physics-based generative models, surrogate models, data assimilation & digital twins, physics-based reasoning and the interpretation of physical results using AI.
Responsibilities
- Identify, recruit and hire a team of scientists in Physics Informed AI with a focus on design
- Work closely with a multi-disciplinary team of research scientists and engineers to conceive, plan, develop, and implement scientific research projects
- Direct & perform research on machine learning models combining physics simulation and measurement data
- Manage a team, perform bi-annual evaluations, plan development, coach, mentor and connect your personnel to academic communities and throughout the company
- Publish papers in peer-reviewed scientific journals/conferences
- Supervise researchers, engineers and interns (undergrad, Masters, PhD or Post-docs)
- Document and communicate the intent and the results of projects in clear terms to both technical and non-technical team audiences
- Present research findings at conferences and participate in research collaborations with external research institutes and universities
- Communicate and promote the use of research findings throughout Autodesk
- Consult with product teams on the implementation of research findings into products
Minimum Qualifications
- Ph.D. or MSc. 12+ years experience in Computer Science, Engineering, Physics or Applied Mathematics
- Extensive experience with Physics Informed Machine learning models
- Experience authoring physics-based solvers eg; fluids, thermal, structural, kinematic
- Strong publication history in relevant conferences and journals
- Proven track record as a practitioner of ML, creating, training and leading groups that can build and train models at scale
- Excellent written and oral communication skills
- Excellent knowledge of Numerical Methods
- Ability to quickly learn new technologies and adapt to new situations
- Ability to collaborate effectively with a diverse, multicultural global team of scientists, engineers and architects
Preferred Qualifications
- Knowledge of geometry and topology
- Experience training large-scale, multi-modal models and ensembles
- Familiar with collaborative development environments and version control systems
- Experience with:
- 2D and 3D computer graphics programming
- Visualization techniques
- Bayesian statistics
- NVIDIA Warp and/or JAX, NVIDIA Modulus or similar
- Pytorch, Pytorch Lightning, Weights & Biases, Ray, AWS Sagemaker
- Experience training diverse architectures: CNNs, GNNs, Diffusion models, Contrastive learning, Transformers, LLMs, RNNs etc. at scale
- Koopman, DMD, SINDy, Fourier Neural Operators, PINNs etc.
- Computer Vision
- Python, C++, Rust
- OpenMP, Clang, SIMD, etc.