Principal Architect Performance Analysis and Modeling
AI-infrastructure company producing memory-centric hardware, networking, and software for low-latency generative-AI inference in data centers.
Funding history
About d-Matrix
d-Matrix develops digital in-memory-compute technology and a full-stack inference platform comprising Corsair accelerators, JetStream networking accelerators, and Aviator software.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will analyze emerging machine learning workloads, create analytical models for current and future hardware, and propose hardware and software features that improve inference acceleration. You will track relevant research and collaborate with product, hardware design, compiler, inference server, and kernel partners.
Requirements
- BSEE with 10+ years of industry experience or MSEE with 8+ years of industry experience
- Knowledge of computer architecture, hardware-software co-design, performance modeling, and machine learning fundamentals
- Fluency in C/C++ or Python
- Experience developing analytical performance models or architecture simulators
Responsibilities
- Analyze emerging machine learning algorithms and workloads
- Identify functional and performance implications of workloads
- Create analytical models for current and future hardware performance
- Propose hardware and software features that enable or accelerate algorithms
- Track research in machine learning architecture and algorithms
- Collaborate with product, hardware design, compiler, inference server, and kernel teams
Benefits
- Medical insurance
- Dental insurance
- Vision insurance
- 401k
- Equity
- Bonus