Назад
Company hidden
обновлено 10 дней назад

Senior ML Engineer (Model Compression)

128 700 - 261 300$
Формат работы
remote (только USA)/hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
Релокация
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/

TL;DR

Senior ML Engineer (Model Compression): Developing and iterating on quantization and compression strategies for AV models with an accent on numerical robustness, safety, and low-latency deployment. Focus on advancing numerical sensitivity analyses, building automated low-precision deployment flows, and bridging the gap between SOTA research and safety-constrained automotive hardware.

Location: Remote (US). Candidates living within a specific radius of GM hubs (Austin, Mountain View, Sunnyvale) are expected to report to the office three times a week.

Salary: $128,700 – $261,300

Company

hirify.global is an automotive leader working towards a world with zero crashes, zero emissions, and zero congestion.

What you will do

  • Develop quantization and compression strategies for AV models targeting NVIDIA-based hardware.
  • Conduct numerical sensitivity analyses to define safe compression policies per operator, layer, or block.
  • Build automated tooling and connected flows to make low-precision deployments repeatable and reliable.
  • Bridge the gap between state-of-the-art model compression research and safety-constrained production deployment.
  • Collaborate with deployment, compiler, and Embodied AI teams to support compression-aware modeling.

Requirements

  • Bachelor's degree in CS, EE, Physics, Mathematics, Data Science/ML, or a related quantitative field.
  • 3+ years of industry experience in model optimization, quantization, or efficient inference.
  • Strong proficiency in PyTorch and experience with graph-level representations (PyTorch FX, ONNX).
  • Solid background in numerical linear algebra and optimization (conditioning, Jacobians, Hessians).
  • Must be based in the United States.

Nice to have

  • Master's or PhD degree in related quantitative fields.
  • Deep experience with PTQ, QAT, and frameworks like PT2E, ModelOpt, or torchao.
  • Knowledge of advanced algorithms such as GPTQ, AWQ, SmoothQuant, QuIP, or SparseGPT.
  • Experience with perception or transformer-based models (BEV backbones, detection/segmentation) in AV/ADAS.
  • Experience with edge deployment on automotive SoCs or robotics platforms.

Culture & Benefits

  • Comprehensive medical, dental, and vision insurance.
  • Health Savings Account (HSA) and Flexible Spending Accounts (FSA).
  • Retirement savings plan and life insurance.
  • Paid vacation, holidays, and sickness benefits.
  • Tuition assistance programs and employee assistance program.
  • GM vehicle discounts.

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 →