ByteDance
Edge ML Software Engineer: System Modeling- PICO- San Jose
San Jose, California · Full-time · Posted Oct 28, 2026
- Experience
- 3+ years of industry experience; preferred: 5+ years of relevant industry experience.
- Education
- Bachelor's degree in Computer Science, Electrical Engineering, Computer Engineering, or a related field, or equivalent practical experience.
About the job
Develop transaction-level models of edge NPU architectures and analyze ML workloads to support latency, memory, and power optimization.
What you'll do
- Build bit-accurate NPU models with approximate timing and power accuracy to simulate CNN and Transformer workloads.
- Analyze ML compute intensity, memory footprint and bandwidth needs, and operator-level latency.
- Collaborate with compiler and algorithm teams to optimize workloads for latency, memory, and power targets.
What they ask for
- Bachelor's degree in Computer Science, Electrical Engineering, Computer Engineering, or a related field, or equivalent practical experience.
- 3+ years of industry experience in computer architecture and electronic system modeling.
- Strong understanding of computer architecture concepts, including memory, cache, DMA, tiling, vectorization, and systolic arrays.
- Strong C/C++ and System C proficiency.
Nice to have
- Experience building analytical performance and power models for ML accelerators.
- Experience analyzing performance bottlenecks and generating actionable architectural recommendations.
Tools
C/C++, System C, CNNs, Transformers
AI focus
Model and optimize edge NPU execution of ML workloads, including CNNs and Transformers.
Model-written summary · the original posting is authoritative