AI Systems Architecture Intern — Memory & LLM Research

Samsung Electronics America

San Jose (CA)

On-site

USD 39,000 - 94,000

Part time

6 days ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Relocation Support
Housing Stipend
Give Back
Emotional Wellness

Job summary

Samsung Electronics America invites applications for an Intern, AI System Architecture Research Scientist in San Jose, CA. You will study memory hierarchies for AI inference, model long-context workloads, and develop performance models.

The role emphasizes research, collaboration with engineers, and potential publications. You will explore memory architectures combining HBM, near-memory compute, and KV-cache techniques, delivering results to guide future product directions and architecture

Qualifications

  • PhD student with 3+ years studying Computer Science or related field.
  • At least 1 academic quarter/semester remaining.
  • Strong background in AI system architecture and memory systems (memory hierarchy, DRAM/HBM).
  • Experience in performance analysis and modeling of AI systems.
  • Hands-on research managing model state across memory tiers (KV-cache paging, reuse, offloading, compression).
  • Strong Python and C/C++ programming skills; experience with PyTorch.

Responsibilities

  • Characterize memory architectures for AI inference and agentic workloads.
  • Build and extend performance models and simulators; perform design-space explorations.
  • Publish results at top-tier venues and contribute invention disclosures.
  • Collaborate with architects and memory technologists; translate research into product directions.

Skills

Python
C/C++
PyTorch
Performance modeling

Education

PhD student

Tools

vLLM
SGLang
LMCache

Job description

Samsung Electronics America invites applications for an Intern, AI System Architecture Research Scientist in San Jose, CA. You will study memory hierarchies for AI inference, model long-context workloads, and develop performance models.

The role emphasizes research, collaboration with engineers, and potential publications. You will explore memory architectures combining HBM, near-memory compute, and KV-cache techniques, delivering results to guide future product directions and architecture

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

AI Systems Architecture Research Intern
AI Systems Architecture Research Intern

samsungsemiconductor • San Jose (CA)

On-site
USD 55,000 - 83,000
Intern, AI System Architecture Research Scientist
Intern, AI System Architecture Research Scientist

samsungsemiconductor • San Jose (CA)

On-site
USD 55,000 - 83,000
AI Systems Performance Intern — Benchmark & Profiling
AI Systems Performance Intern — Benchmark & Profiling

Samsung Electronics America • San Jose (CA)

On-site
USD 39,000 - 94,000
Relocation Support
Housing Stipend
Give Back programs
+2
AI Systems Performance Intern: Memory & Benchmarking
AI Systems Performance Intern: Memory & Benchmarking

samsungsemiconductor • San Jose (CA)

On-site
USD 39,000 - 94,000
Relocation Support
Housing Stipend
Charitable giving match
+3
Principal AI Memory Architect
Principal AI Memory Architect

Conductor • San Jose (CA)

On-site
USD 219,000 - 351,000
Medical/Dental/Vision/401k
4+ weeks paid time off
Fertility/adoption support
HBM Architecture Intern: AI Memory & Systems Research
HBM Architecture Intern: AI Memory & Systems Research

Micron Technology, Inc. • Richardson (TX)

On-site
USD 28,000 - 50,000
Health benefits
Paid time off
Paid holidays
AI Systems Intern: LLM Inference & SoC Hardware
AI Systems Intern: LLM Inference & SoC Hardware

Samsung • Folsom (CA)

On-site
USD 39,000 - 94,000
Relocation Support
Housing Stipend
Volunteer/community giving
HBM Design Architecture Intern — AI Memory Systems
HBM Design Architecture Intern — AI Memory Systems

Micron Technology, Inc. • Richardson (TX)

Hybrid
USD 20,000 - 30,000
Medical/dental/vision plans
Paid time off
Director, AI Memory & Large-Scale Inference
Director, AI Memory & Large-Scale Inference

Samsung Electronics America • San Jose (CA)

Hybrid
USD 219,000 - 351,000
4+ weeks PTO
Fertility care stipend
Medical travel support
+1
Director of AI Solutions Architecture (Memory & Systems)
Director of AI Solutions Architecture (Memory & Systems)

SK hynix America • San Jose (CA)

On-site
USD 250,000 - 320,000
Top Tier health insurance at no cost
Paid day offs: PTO, company holidays,
401k Matching
+4