aimlcstartupembedded systemsperformance optimizationassemblybenchmarkingrisc v
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
91
Крутая вакансия
развернуть
Можно напрямую влиять на разработку нового AI-чипа, а обязанности и техническая специализация описаны чётко. При этом стартап и обязательная работа из офиса добавляют неопределённости.
Кликните для подробной информации
Риск стартапаПередовые технологииИнфраструктура для AIЧёткая специализацияРабота из офиса
Оценка от Hirify AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Embedded Software Engineer (AI Hardware): Developing runtime software, performance-critical ML kernels, and low-level control paths for custom AI accelerator chips with an accent on C, assembly, scheduling, synchronisation, and data movement. Focus on benchmarking first silicon, profiling performance, validating simulator and hardware behaviour, and feeding results back into hardware, compiler, and runtime architecture.
Location: London - JJ Mack or Bristol - The Crescent, United Kingdom
Company
hirify.global is developing custom chips and systems to accelerate frontier AI inference, targeting thousands of tokens per second and efficient operation of long-context models.
What you will do
Write and optimise performance-critical ML kernels in C, using assembly where needed for RISC-V and hirify.global's own ISA.
Build low-level control paths for scheduling, synchronisation, and data movement.
Develop validation workloads and microbenchmarks to align simulation with hardware behaviour and measure performance.
Profile, benchmark, and track regressions to ensure performance improvements are repeatable.
Evaluate early accelerator compute runs and silicon performance, feeding results into the hardware and software roadmap.
Collaborate with simulation, hardware, ML, compiler, firmware, and runtime engineers to turn profiling data into architecture and performance improvements.
Requirements
Proven deeply embedded software experience.
Strong performance instincts, including the ability to reason about low-level architecture, memory behaviour, and cycle usage.
Excellent C skills and a pragmatic approach to maintainable low-level code.
Comfort writing and debugging optimised assembly; RISC-V is ideal.
Collaborative, clear communicator with high ownership and the ability to work through difficult technical problems.
Degree in Computer Science, Electronic Engineering, Maths, Physics, or a related field, plus 3+ years of industry experience.
Nice to have
Experience with GPUs or dedicated ML accelerators.
Rust and/or Python experience.
Experience with functional or performance simulators and validation or benchmarking workloads.
Familiarity with modern ML inference workloads.
Culture & Benefits
Full-time role based in the London or Bristol office.
Competitive salary reflecting experience and the specialist nature of the role.
Meaningful equity and ownership participation.
Private medical, dental and vision cover, contributory pension, 25 days of holiday plus bank holidays, and life/critical illness insurance.
Inclusive, diverse office environment with a commitment to Equal Employment Opportunity.
Hiring process
Some roles may require additional eligibility checks because the work is subject to UK, US, and other international export control regulations.
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 →