Deep Learning Engineer

A high-tech company developing advanced technologies in wireless communication, smart sensing, and artificial intelligence for software and semiconductor applications.

The company is located in the Sharon area and employs several hundred professionals.

Role overview

• Part of the LiteML team, responsible for developing a Python-based package for model quantization and pruning to enable efficient deployment of neural networks on NPUs and embedded targets.
• Builds algorithms and tools that bridge research prototypes to production-ready SDK components.
• Designs and implements LiteML features, including post-training quantization, QAT hooks, structured/unstructured pruning, calibration, and model-accuracy recovery.
• Collaborates with architecture, software, embedded, and research teams.
• Engages with academia and clients to support research and deployment needs.
• Designs APIs, implements core algorithms in Python, writes tests, and manages package releases.

Requirements:

• Relevant BSc degree.
• 3+ years of experience building ML tooling, frameworks, or ML-adjacent infrastructure.
• Strong development experience in Python.
• Knowledge of C/C++.
• Solid understanding of deep learning concepts.
• Experience with Git and modern code review/CI workflows on Linux.