Explore new AI model architectures to run optimally on an edge compute with memory constraints.
Drive breakthroughs by converting ANN models (such as CNNs and Transformers) to those that operate efficiently with reduced memory using paradigms like SNN, SSM, sparsity, or RNN
Support proof of concept advancing model retraining, optimization, and compression

Requirements

PhD Intern in electrical engineering, computer engineering, computer science, or a related field.
Deep understanding in AI model architecture, ANN/SNN/ SSM /Sparsity
Vast knowledge in Edge AI model Compression, Optimization, and Compilation
Proficient with multiple frameworks, including Snntorch, PyTorch, TVM, TensorFlow, CUDA, C/C++, and Python
Familiar with analog compute, in-memory compute, sparse compute, and neuromorphic systems.
Strong analytical mindset with the ability to balance performance, power, and memory tradeoffs.
Experience with the physical world, including vision, 3D point clouds, tactile, audio – Advantage

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills & Tools

AI model architectureANNSNNSSMsparsityRNNmodel compressionmodel optimizationmodel compilationprogramming in C/C++

Soft Skills

analytical mindset

Certifications

PhD in electrical engineeringPhD in computer engineeringPhD in computer science