Deep Learning Performance Intern - 2027
Core
Optimize deep learning hardware and software architecture for edge devices, workstations, and data center GPUs.
Role type
Deep Learning Performance Architect (Intern)
Builds
Accelerated deep learning workloads for automotive, robotics, LLMs, and generative AI.
Domain
Hardware/Software Systems, Deep Learning, Computer Architecture
Deliverable
production ML models
Required skills
GPU/NPU architecture, deep learning algorithm analysis, performance modeling, system bottleneck identification, LLM/generative AI kernel optimization, system architecture design, ML framework familiarity
Preferred skills
None stated
Technologies
GPU, NPU, LLM, generative AI, deep learning frameworks
