Unconventionalinc

System Modeling (Performance Models)

Palo Alto, CA I US Remote

Sponsorship not specifiedDetected 49 days ago

PythonMachine LearningTensorFlowPyTorchNumPyElectrical EngineeringResearchCommunication

About the role

The role involves development of physics-based system models, GPU-accelerated ML system simulations, and cross-layer system integration.
You don't need to be an expert in all of these, but you have to be very strong in at least one, and solid in the rest.

Building extensible and composable high-fidelity power, performance and area estimation tools for novel AI acceleration system architectures to enable rapid design space exploration.
Define and create comparative analyses across candidate architectures and existing state-of-art implementations.
Working with other teams to understand their needs for such modeling and simulation to support high level system design as well as lower level verification of hardware.
Enjoy massive ownership and an outsized opportunity to drive change.

Experience with tools and development for power profiling, modeling and simulation for AI workloads.

While the minimum qualifications focus on the core modeling and ML expertise, candidates who possess the following qualities will be the most impactful.
Dynamic systems knowledge
Basic familiarity of analog dynamic systems, including transient responses, nonidealities such as nonlinearity, quantization, random noise, and feedback/stability
Software engineering
Experience with PyTorch internals: autograd, custom modules, low-level ops
familiarity with torch.compile or similar graph capture/compile flows.
Experience with CUDA, Triton, or other GPU programming approaches (writing custom kernels, understanding memory hierarchy, basic performance tuning).

Familiar with different existing systolic array accelerator architectures for AI/ML workloads
ML and systems fluency
Solid understanding of modern AI/ML architectures and training/inference workflows.
modular design, testing, packaging, CI.
Comfort with at least some of: JAX, NumPy, TensorFlow, Modal, HPC patterns (MPI, NCCL, distributed training), SciPy.
Systems thinking
Demonstrated ability to reason across multiple layers of the stack: algorithm, software, runtime, hardware.
Experience applying at least some efficiency techniques (quantization, sparsity, pruning, distillation, kernel fusion, etc.).
Modeling / simulation mindset
Why Join Us?
The Mission: Redefine computing for the next 50 years by solving the fundamental energy limitation of AI at a global scale.
The

A comprehensive package including best-in-class health benefits, 401k matching, truly unlimited PTO, and complimentary meals when working from our Palo Alto office.

This listing is sourced directly from Unconventionalinc's careers page and normalized into a canonical job model.