Intern, Architecture Research Engineer (MoE Placement for Serving at Scale)
SSI San Jose internship
On Site
entry
H1B: yes
Samsung Semiconductor Intern, Architecture Research Engineer focused on Mixture-of-Experts (MoE) model serving at Samsung Semiconductor. Works on optimizing expert placement, extending simulators, and integrating placement-aware scheduling.
Responsibilities
The AGI (Artificial General Intelligence) Computing Lab is dedicated to solving the complex system-level challenges posed by the growing demands of future AI/ML workloads. Our team is committed to designing and developing scalable platforms that can effectively handle the computational and memory requirements of these workloads while minimizing energy consumption and maximizing performance. To achieve this goal, we collaborate closely with both hardware and software engineers to identify and address the unique challenges posed by AI/ML workloads and to explore new computing abstractions that can provide a better balance between the hardware and software components of our systems. Additionally, we continuously conduct research and development in emerging technologies and trends across memory, computing, interconnect, and AI/ML, ensuring that our platforms are always equipped to handle the most demanding workloads of the future. By working together as a dedicated and passionate team, we aim to revolutionize the way AI/ML applications are deployed and executed, ultimately contributing to the advancement of AGI in an affordable and sustainable manner. Join us in our passion to shape the future of computing!
Location: Daily onsite presence at our San Jose headquarters in alignment with our Flexible Work policy
Reports to: Sr. Director
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.
Work closely with the compiler and runtime teams to integrate placement-aware scheduling.
Contribute to ML systems and architecture research and write research papers.
Stay up-to-date with the latest trends and advancements in ML architectures and LLM serving.
Complete other responsibilities as assigned.
Pursuing Masters, or PhD in Computer Science or Electrical Engineering preferred.
Qualification
Pursuing MastersPublished papers in MicroarchitectureBackground in optimization methods (e
Required
Pursuing Masters, or PhD in Computer Science or Electrical Engineering preferred
Must have at least 1 academic quarter/semester remaining
Research experience in distributed ML systems or AI hardware such as GPUs, TPUs, and NPUs
Experience in developing simulators or performance models for large-scale ML systems
Understanding of system level characteristics of MoE inference and expert parallelism
Strong analytical and problem-solving skills
Excellent communication and interpersonal skills
Ability to work independently and as part of a team
Preferred
Published papers in Microarchitecture, Systems, or ML Systems conferences
Background in optimization methods (e.g., integer linear programming or graph partitioning)