Be an early applicantLess than 25 applicants

Company

Tenstorrent · 16 hours ago

Sr. Principal High-Performance Computing Architect

United States

Full-time

Remote

Senior Level, Lead/Staff

$100K/yr - $500K/yr

15+ years exp

Maximize your interview chances

Application Specific Integrated Circuit (ASIC)Artificial Intelligence (AI)

Comp. & Benefits

H1B Sponsor Likely

Insider Connection @Tenstorrent

Discover valuable connections within the company who might provide insights and potential referrals.
Get 3x more responses when you reach out via email instead of LinkedIn.

Responsibilities

Conduct performance analysis, benchmarking, and write performance models to identify performance bottlenecks, optimize system parameters, and guide architectural enhancements.

Design and develop high-performance computing architectures that deliver exceptional computational performance, scalability, and energy efficiency.

Collaborate with hardware engineers to design and optimize the system's computational components, including processors, accelerators, interconnects, and memory subsystems.

Work closely with software developers to define and implement software development frameworks, libraries, and tools that maximize performance and productivity on the target HPC architecture.

Define system-level requirements, including processing power, memory capacity, I/O bandwidth, storage capabilities, and ensure compliance with industry standards and customer expectations.

Evaluate and select appropriate technologies, including processors, accelerators, and network fabrics, based on application requirements, performance & power characteristics, and cost considerations.

Collaborate with domain experts and application developers to understand the unique requirements of specific scientific, research, or data-intensive workloads and propose tailored architectural solutions.

Stay up-to-date with the latest advancements in HPC hardware, software, and industry trends to guide future system designs and technology adoption.

Work closely with vendors and suppliers to evaluate emerging HPC technologies, assess their suitability for specific applications, and negotiate supply agreements.

Provide technical guidance and mentorship to junior team members, fostering knowledge sharing and best practices within the HPC architecture domain.

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.

High-Performance ComputingC++Performance ModelingParallel ProgrammingHPC Architecture DesignGEM5SSTOpenMPMPICUDAOpenCLInfiniBandEthernetOmni-PathCFortranPythonCollaboration Skills

Required

15+ years of experience

Experience coding performance models in C++

Bachelor's or Master's degree in Computer Engineering, Electrical Engineering, or a related field. A Ph.D. is a plus.

Strong expertise in high-performance computing architecture design, including processors, accelerators, interconnects, and memory subsystems.

Experience developing new architectures using large scale performance simulation environments, for example GEM5 or SST

Experience analyzing workload behavior on large systems using open-source or custom software tools

Proven experience in designing and optimizing HPC architectures for scientific, research, or data-intensive applications.

Proficiency in parallel programming models and frameworks, such as OpenMP, MPI, CUDA, or OpenCL, and their application to HPC workloads.

Solid understanding of performance analysis and optimization techniques for parallel computing, including profiling, tracing, and performance counters.

Familiarity with industry-standard interconnects and network fabrics, such as InfiniBand, Ethernet, or Omni-Path, and their impact on HPC system performance.

Knowledge of memory subsystems and memory hierarchy designs, including cache coherence protocols, memory models, and NUMA architectures.

Experience with HPC software stack components, such as compilers, runtime systems, job schedulers, and scientific libraries.

Strong programming skills in languages commonly used in HPC, such as C, C++, Fortran, or Python.

Excellent problem-solving abilities and the ability to analyze and address complex performance and scalability challenges.

Strong communication and collaboration skills to work effectively with cross-functional teams and domain experts.

Benefits

Highly competitive compensation package and benefits

Company

Tenstorrent

Tenstorrent is a computing company that develops processors designed to help in faster training and adaptability to future algorithms.

Founded in 2016

Toronto, Ontario, CAN

201-500 employees

http://tenstorrent.com

H1B Sponsorship

Tenstorrent has a track record of offering H1B sponsorships. Please note that this does not guarantee sponsorship for this specific role. Below presents additional info for your reference. (Data Powered by US Department of Labor)

Distribution of Different Job Fields Receiving Sponsorship

Represents job field similar to this job

Trends of Total Sponsorships

2023 (16)

2022 (6)

2021 (40)