ML Research Scientist
Core
Design algorithms and quantization schemes for efficient, high-accuracy inference on analog in-memory compute platforms.
Role type
ML Research Engineer (analog hardware)
Builds
Deep neural network inference on custom silicon
Domain
Hardware-aware machine learning / Analog computing
Deliverable
production ML models
Required skills
Quantization methods (PTQ, QAT), Matrix-vector multiplication algorithms, Numerical methods for DNNs, Python, PyTorch
Preferred skills
Contributions to quantization libraries, Publications in top-tier ML venues, Analog computation expertise, Hardware team collaboration
Technologies
Python, PyTorch
Responsibilities
Research and develop novel analog-aware quantization methods, Design mathematically principled matrix-vector multiplication algorithms, Collaborate with analog hardware engineers to define algorithmic requirements
Seniority
Senior, hands-on IC
