Architecture Research Engineer Intern - MoE Placement for Serving at Scale
SamsungAdded 13h ago
San Jose, CAInternship
Save this job and browse the whole board.
Create free account
No credit card needed
What you'll do
- Research MoE model placement, replication, and migration for distributed serving.
- Optimize expert placement alongside memory hierarchy and interconnect topology.
- Develop analytical simulators and tools to model large-scale AI serving.
- Collaborate with compiler and runtime teams on placement-aware scheduling.
What they're looking for
- Currently pursuing a Master’s or PhD in CS or Electrical Engineering.
- Research experience with distributed ML systems or AI hardware.
- Proficiency in PyTorch, JAX, or LLM serving frameworks.
- Ability to work onsite daily in San Jose, California.
Pay and perks
- Hourly base pay range of $28 to $68 USD.
- Includes relocation and housing stipends for eligible interns.
Summarized by newgrad.ai from Samsung's public posting. Check the original for full details before you apply.
Apply on Samsung's site.
Apply nowListing wrong or expired, or you're the employer and want it removed? Let us know.
