ByteDance
Edge ML Software Engineer: Model Optimization- PICO- San Jose
San Jose, California · Full-time · Posted Oct 28, 2026
- Experience
- 3+ years of industry experience in machine learning software engineering, model deployment, or ML systems for production environments; preferred: 5+ years.
- Education
- Master's degree in Computer Science, Electrical Engineering, Computer Engineering, or a related field, or equivalent practical experience.
About the job
Optimizes and deploys machine-learning models on edge NPUs, profiling performance and power and resolving issues with cross-functional teams.
What you'll do
- Convert and compile ML models for edge NPUs and apply quantization.
- Profile model performance and power; identify compute, memory, data-movement, and scheduling bottlenecks.
- Apply hardware-aware optimizations and collaborate with algorithm, compiler, firmware, and hardware teams to debug issues.
What they ask for
- Strong understanding of deep learning architectures, including CNNs and Transformers.
- Knowledge of ML accelerator architectures, operator fusion, memory hierarchies, and data movement.
- Practical experience with PyTorch or TensorFlow.
- Proficiency in Python and C/C++.
Nice to have
- 5+ years of industry experience in machine learning software engineering, model deployment, or ML systems for production environments.
- Understanding of edge inference constraints and optimization, including quantization techniques such as PTQ and QAT.
Tools
edge NPUs, PyTorch, TensorFlow, Python, C/C++, CNNs, Transformers, PTQ and QAT
AI focus
Deploys and optimizes machine-learning models for edge NPUs, including quantization, compression, and operator fusion.
Model-written summary · the original posting is authoritative