- מיקום
- כל הארץ
- היקף משרה
- משרה מלאה
- תפקיד
- מתכנת/ת צד שרת
תיאור המשרה
About the Role:
In this role, you will build deep expertise in AI fundamentals, LLM and generative AI network architectures, and their underlying algorithms. You will continuously research emerging generative AI architectures across the industry, staying ahead of how the field evolves.
A central focus will be quantization – understanding, developing, and refining quantization methods and algorithms, and driving their deployment on our hardware to achieve maximum performance without compromising accuracy.
Responsibilities:
- Explore and plan end to end network deployment on Ceva%27s hardware.
- Own network accuracy measurement and improvement.
- Develop the graph compiler%27s hardware-aware quantization tool.
- B.Sc/M.Sc. in Engineering, Computer Science, or related technical field.
- 3-4 years of experience as a Python developer.
- Experience working with PyTorch.
- Experience evaluating and running ML/AI models, with knowledge of common architectures.
- Proficient in using AI tools, backed by solid testing practices.
- Strong communication skills, self-driven, with solid time management.
Advantages:
- Experience with LLMs.
- Experience with networks quantization methods.
- Experience with HuggingFace, PyTest and Jenkins.