Sr. Principal Heterogeneous Memory Architect
Santa Clara, CA, USA
Posted on Saturday, June 3, 2023
Tenstorrent is leading the industry on cutting-edge AI technology, revolutionizing performance expectations, ease of use, and cost efficiency. With AI redefining the computing paradigm, solutions must evolve to unify innovations in software models, compilers, platforms, networking, and semiconductors. Our diverse team of technologists have developed a high performance RISC-V CPU from scratch, and share a passion for AI and a deep desire to build the best AI platform possible. We value collaboration, curiosity, and a commitment to solving hard problems. We are growing our team and looking for contributors of all seniorities.
We are seeking a highly skilled and experienced Heterogeneous Memory Architect to join our team. As a Heterogeneous Memory Architect, you will be responsible for designing and implementing memory architectures that utilize various memory technologies to optimize performance, power efficiency, and cost for complex computing systems. You will work closely with cross-functional teams, including hardware engineers, software developers, and system architects, to ensure seamless integration of memory subsystems.
- Design and develop heterogeneous memory architectures for high-performance computing systems, embedded devices, or data center applications.
- Evaluate and select appropriate memory technologies, such as DDR, HBM, GDDR, NVRAM, and emerging non-volatile memory technologies, based on system requirements.
- Define memory subsystem specifications, including capacity, bandwidth, latency, and power requirements, and ensure compliance with industry standards.
- Collaborate with hardware and software teams to optimize memory subsystem performance, including cache coherence, memory hierarchy, and data management.
- Conduct architectural analysis, performance modeling, and simulations to identify bottlenecks and propose design improvements.
- Work closely with vendors and suppliers to assess new memory technologies, evaluate their suitability for specific applications, and negotiate supply agreements.
- Participate in the development of memory controllers, interconnects, and memory management units (MMUs) to ensure efficient memory utilization and data movement.
- Stay up-to-date with the latest advancements in memory technologies, architectures, and industry trends to guide future memory system designs.
- Provide technical guidance and mentorship to junior team members, promoting knowledge sharing and best practices.
- Collaborate with cross-functional teams to define system-level memory requirements, ensuring compatibility with other hardware and software components.
Experience & Qualifications
- Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, or a related field. A Ph.D. is a plus.
- Strong expertise in computer architecture, memory systems, and memory technologies.
- Proven experience in designing and optimizing heterogeneous memory architectures for complex computing systems.
- Proficiency in hardware description languages (HDLs) and simulation tools (e.g., Verilog, SystemVerilog, ModelSim).
- Solid understanding of memory controller designs, cache coherence protocols, and memory management techniques.
- Familiarity with industry-standard memory interfaces and protocols, such as DDR, HBM, GDDR, and PCIe.
- Experience with memory performance analysis, modeling, and simulation tools (e.g., CACTI, RAMulator, DRAMSim).
- Knowledge of emerging memory technologies (e.g., persistent memory, 3D XPoint, MRAM) and their architectural implications.
- Strong problem-solving skills and the ability to analyze complex system-level issues.
- Excellent communication skills and the ability to collaborate effectively with cross-functional teams.
Compensation for all engineers at Tenstorrent ranges from $100k - $500k including base and variable compensation targets. Experience, skills, education, background and location all impact the actual offer made.