Tenstorrent · 3 days ago
Staff SOC Performance Architect
Maximize your interview chances
Application Specific Integrated Circuit (ASIC)Artificial Intelligence (AI)
Comp. & BenefitsNo H1B
Insider Connection @Tenstorrent
Get 3x more responses when you reach out via email instead of LinkedIn.
Responsibilities
Gather, refine and document Computer Vision, Machine Learning and other automotive workloads
Work with internal teams to map automotive workloads to Tenstorrent architecture.
Run automotive ML workloads on performance models. Analyze and summarize results.
Develop SoC and subsystem level performance use case descriptions.
Develop models of interconnect and memory subsystem behavior for target workloads
Analyze workload in detail and give guidance on improvements at both module and chip level.
Create clear documentation of findings and recommendations for performance improvement.
Present results to internal stakeholders and customers
Participate in competitive analysis, comparing achieved performance to other industry solutions
Qualification
Find out how your skills align with this job's requirements. If anything seems off, you can easily click on the tags to select or unselect skills to reflect your actual expertise.
Required
Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, or a related field.
Strong expertise in C/C++ and Python based modeling for SoCs
Solid understanding of at least 3 ML network architectures and their performance characteristics.
Experience with running ML models on GPU architectures.
Experience with CUDA / CUDNN / pytorch.
Solid understanding of computer architecture, interconnects and memory system behavior
Proven experience in modeling and analyzing complex workloads for SoCs.
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.
Preferred
A Ph.D. is a plus.
Company
Tenstorrent
Tenstorrent is a computing company that develops processors designed to help in faster training and adaptability to future algorithms.
Funding
Current Stage
Growth StageTotal Funding
$334.55MKey Investors
FidelityEPIQ Capital GroupEclipse Ventures
2023-08-02Series Unknown· $100M
2021-05-20Series C· $200M
2019-02-02Series B· $20.7M
Recent News
High-Performance Computing News Analysis | insideHPC
2024-11-14
2024-11-12
2024-11-10
Company data provided by crunchbase