Samsung Semiconductor is looking for innovative memory solutions for AI/ML workloads, specifically focusing on LLM models. The role involves researching, developing, and modeling new memory architectures to address performance bottlenecks and trade-offs between memory and computation in AI/ML systems.
Requirements
- Required knowledge, achievements, and skillsets of C/C++, AI/ML framework, LLM models, hands on experience with CPU/GPU server hardware.
- Publication and research experience in HW/SW co-design, FPGA acceleration preferred.
Responsibilities
- Collaborate with other researchers in the team to develop innovative memory solutions for AI/ML workload.
- Performance profiling of GPU/GPU/Accelerator system to analyze the bottleneck.
- Characterize device performance and identify architecture tradeoffs between memory and computation.
- Design simulation models for new architecture solution and collect data for publication.
- Generate research patent/IP report/publication and give talks on the learning.
- Complete other responsibilities as assigned.
Other
- Pursuing PhD in Computer Science or Electrical/Computer Engineering preferred.
- Must have at least 1 academic quarter/semester remaining of computer architecture.
- You’re inclusive, adapting your style to the situation and diverse global norms of our people.
- An avid learner, you approach challenges with curiosity and resilience, seeking data to help build understanding.
- You’re collaborative, building relationships, humbly offering support and openly welcoming approaches.
- Innovative and creative, you proactively explore new ideas and adapt quickly to change.
