pythonc++machine learningnocrdmasstgem5ppa analysisinterconnect architecturechip to chip interfaces
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указана
На похожих ролях по рынку
$64к$76кмедиана$89к
50 в выборке
87
Хорошая вакансия
развернуть
Чётко очерченная исследовательская роль даёт возможность влиять на разработку нового оборудования для AI и HPC, но зарплата не указана, а работать можно только из Германии.
Кликните для подробной информации
Зарплата не указанаТолько ГерманияСовременные инструментыПонятные задачиAI-оборудование30 дней отпуска
Оценка от Hirify AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Senior NoC Research Engineer (Network-on-Chip) (AI/HPC hardware): Modelling and evaluating on-chip and chip-to-chip interconnect architectures for SpiNNext under real machine-learning workloads with an accent on routing, traffic management, protocol analysis, and PPA trade-offs. Focus on building cycle-level simulations, analysing deadlock-free data movement, and making quantitative architecture recommendations for massively parallel accelerator systems.
Location: Remote from Germany; role associated with Dresden, Germany. Up to two weeks of work abroad annually.
Company
hirify.global develops brain-inspired computing hardware and software based on SpiNNaker2 technology, providing remote access to sparse computing resources for AI and HPC.
What you will do
Explore NoC topologies, router and switch designs, arbitration, flow control, QoS, congestion control, and adaptive routing.
Build and maintain architectural models and simulations using SST, gem5, and custom cycle-level or analytical models.
Develop traffic generators representing collective communication, tensor parallelism, and memory traffic in machine-learning workloads.
Analyse power, performance, and area trade-offs and provide quantitative design recommendations.
Translate AXI, CHI, and APB specifications into design requirements while evaluating interconnect IP and chip-to-chip interfaces.
Present research findings to architecture and leadership teams and contribute to publications and patents.
Requirements
PhD, or a Master’s degree with equivalent research experience, in electrical engineering, computer engineering, computer science, or a related field.
Senior-level experience in NoC or interconnect architecture in industry or applied research.
Strong knowledge of NoC topologies, routers, switches, arbitration, flow control, QoS, and congestion control.
Understanding of machine-learning workloads, accelerator architectures, RDMA concepts, InfiniBand, RoCE, and on-chip protocols such as AXI, CHI, or AHB.
Hands-on experience with architectural modelling and simulation, plus strong Python and C++ skills.
Clear written and verbal communication in English is required.
Nice to have
Experience with PCIe, Ethernet, UCIe, HBM, CXL, or massively parallel architectures.
Publications or patents in on-chip networks, interconnect architecture, data movement, ML, or HPC.
Culture & Benefits
Work on sparse-computing technology with direct influence on the SpiNNext architecture.
Collaborate with engineers from academia and industry.
30 days of annual vacation.
Up to two weeks of work abroad per year.
Equity participation in a growing deep-tech company.
Hiring process
Submit a CV, a brief cover letter describing an analysed interconnect or data-movement problem, and optional links to publications, patents, or public code.
Include salary expectations, earliest start date, current location, and whether visa sponsorship or relocation support to Germany is needed.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →