Intern, Architecture Research Engineer (MoE Placement for Serving at Scale)
Samsung Semiconductor
San Jose, California, United States
Internship
1 day ago
AI/ML Hardware
Research expert placement, replication, and migration for Mixture-of-Experts (MoE) serving on distributed AI accelerators.
Originally posted November 18, 2026 by the employer.
About the role
This internship within the AGI Computing Lab focuses on Mixture-of-Experts (MoE) placement as a design problem for serving on distributed accelerators at scale. You will research expert placement, replication, and migration while co-optimizing strategies with memory hierarchy and interconnect topology.
What you'll do
- Research expert placement, replication, and migration for serving Mixture-of-Experts (MoE) models.
- Co-optimize expert placement with parallelism strategy, memory hierarchy, and interconnect topology.
- Characterize expert load imbalance, temporal drift, and cross-layer affinity on real workloads.
- Extend analytical simulators and DSE tools to model MoE serving and evaluate hardware design points.
- Collaborate with compiler and runtime teams to integrate placement-aware scheduling.
- Contribute to ML systems and architecture research and write research papers.
What you'll need
- Currently enrolled in a degree program with at least 1 academic quarter or semester remaining.
- Research experience in distributed ML systems or AI hardware such as GPUs, TPUs, and NPUs.
- Experience developing simulators or performance models for large-scale ML systems.
- Understanding of system-level characteristics of MoE inference and expert parallelism.
- Familiarity with PyTorch or JAX and LLM serving frameworks such as vLLM, SGLang, or TensorRT-LLM.
Nice to have
- Pursuing a Master's or PhD in Computer Science or Electrical Engineering.
- Published papers in Microarchitecture, Systems, or ML Systems conferences.
- Background in optimization methods such as integer linear programming or graph partitioning.
Skills: MoE, distributed ML, simulators, DSE, LLM serving
Market context
- Employer posting date: 18 Nov 2026
- First seen in our index: 18 Nov 2026 (our observation date)
- Last confirmed on the employer's career site: 19 Nov 2026
- Specialty: AI/ML Hardware Engineering (AI ML Hardware)
- Comparable active jobs: 480 at 76 employers, as of 18 Nov 2026
- Related specialties (Software, Firmware & Systems family): 6844 active jobs at 180 employers
View all Samsung Semiconductor jobs · AI chip design jobs · San Jose jobs
How we counted: postings read from employer career sites; dates are our observations unless labelled as the employer's. How we count
Samsung Semiconductor
San Jose, California, United States
On-site
Internship
1 day ago