About the role#
The HBM Architecture team researches and evaluates next-generation memory solutions for artificial intelligence, high-performance computing, and data-intensive applications. As a PhD intern, you will prototype advanced memory and system architecture concepts. You will work with experienced architects to evaluate how memory hierarchy and interconnect design choices affect system performance, power efficiency, and scalability.
What you'll do#
- Research and evaluate memory and system architecture concepts for AI accelerators, including GPUs, TPUs, and custom designs.
- Develop performance models to assess bandwidth, latency, power, scalability, and overall system efficiency.
- Analyze AI training, inference, and HPC workloads to identify system performance bottlenecks.
- Investigate memory hierarchy, HBM, DRAM, cache, storage, and interconnect optimizations.
- Collaborate with cross-functional engineering teams and explore AI and LLM-based tools to improve research workflows.
What you'll need#
- Currently pursuing a PhD in Computer Architecture, Electrical Engineering, Computer Engineering, Computer Science, or a related field.
- 0-2 years of relevant experience in computer architecture, memory systems, or AI hardware.
- Knowledge of memory system architecture, including caches, HBM, DRAM, and interconnect concepts.
- Experience with performance modeling, architectural simulation, or system analysis.
- Proficiency in Python, C++, or similar programming languages.
- Strong analytical, problem-solving, and technical communication skills.
- Research experience in AI accelerators, GPU architecture, or high-performance computing.
- Experience with AI/ML frameworks like PyTorch, TensorFlow, or CUDA-based development.
- Familiarity with architectural simulators, SystemC, GPU profiling tools, or emulation platforms.
- Knowledge of rack-scale systems, scale-up/scale-out architectures, and advanced interconnect technologies.
- Demonstrated research contributions such as publications or conference papers.
Location & details#
- Location: Folsom, California
- Employment Type: Full-time
- Modality: On-site
- Term: Rolling
- Paid Internship: Yes
- Base Salary: $50.24 per hour
About Micron Technology
Micron Technology produces memory and storage solutions including DRAM, NAND, and NOR products. The company operates as a public organization with over 43,000 employees. Founded in 1978, it maintains its headquarters in Boise, Idaho. Micron serves various markets ranging from data centers to mobile devices.
How to get in at Micron Technology
Applying early is a distinct advantage at Micron Technology because recruiters often review candidates before the applicant pool becomes unmanageable. Intern Insider sends an instant alert the moment a role matching your target is published, helping you get your application in among the first. This timing ensures your resume is seen while the team is still actively building their shortlist. You can reach out to recruiters directly to ask about the role or a referral, which often improves your response rate compared to waiting in a queue. Intern Insider surfaces the specific recruiters behind these roles, allowing you to bypass the generic portal and make a professional connection. This approach turns a standard application into a direct conversation.
