About the role#
As an AI Application Engineer intern, you will join the DRAM Design Lab to work on next-generation memory and storage solutions. You will focus on the performance and architecture of LLM inference services, specifically testing how memory systems handle high-demand AI workloads. You will work directly with mentors and cross-functional teams to bridge the gap between software serving requirements and hardware controller design.
What you'll do#
- Deploy and operate an LLM inference service on a 4 × NVIDIA H200 GPU server.
- Build an automated benchmark harness to replay request traces and record latency and throughput.
- Configure KV cache offloading to network-attached storage using NVMe-oF and RDMA.
- Run daily experiment sweeps across varying request rates, context lengths, and cache sizes.
- Maintain experiment configurations and results in git.
- Analyze performance data with Python to identify bottlenecks across the GPU, network, and SSD.
- Collaborate with FPGA, SoC, and firmware engineers to debug the end-to-end data path and validate KV cache correctness.
- Summarize storage requirements to inform future SSD controller architecture.
- Present your findings to the team at the conclusion of your internship.
What you'll need#
- Pursuing a Bachelors, Masters, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
- At least one academic quarter or semester remaining in your degree program.
- Hands-on experience running LLM inference with Python and PyTorch on NVIDIA GPUs in a Linux environment.
- Familiarity with serving frameworks such as vLLM, SGLang, or Hugging Face TGI.
- Understanding of LLM serving internals, including KV cache, prefix caching, batching, parallelism, and latency metrics.
- Experience with system performance benchmarking, profiling, and data analysis scripts.
- Familiarity with KV cache offloading, RDMA/RoCE, NVMe/NVMe-oF storage, and container technologies is preferred.
Location & details#
- This is a full-time, paid internship.
- The role is based on-site at our San Jose, California headquarters.
- This position follows a rolling term schedule.
About Samsung Semiconductor
Samsung Semiconductor operates as a subsidiary of Samsung Electronics. The company manufactures semiconductor components for device makers. It started operations in 1974. The organization employs more than 10,000 people.
How to get in at Samsung Semiconductor
Applying to Samsung Semiconductor early matters because recruiters review applications as they arrive. Intern Insider sends an instant alert the moment a role matching your target is published anywhere, so you apply among the first, early applicants get seen before the pile grows. You should aim to be in the first wave of candidates to ensure your resume reaches a human reader. Reaching out to the right person often helps you stand out from the general applicant pool. Intern Insider surfaces the recruiters behind the company's roles so you can reach out directly to ask about the role or a referral, which materially improves response rates. A brief, professional message to a recruiter can clarify your interest and help you learn more about the team.
