Назад
Company hidden
3 часа назад

Staff Machine Learning Engineer (Edge AI)

Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US/Taiwan
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
Staff Machine Learning Engineer (Edge AI): Designing the complete ML ecosystem for resource-constrained edge devices, from cloud-native MLOps and data lifecycle systems to secure, hardware-aware model optimization with an accent on agentic AI, on-device monitoring, and custom NPU inference. Focus on building autonomous agents, preventing model injection, collaborating with silicon and RTL teams, and optimizing models at graph and operator levels.

Location: Taipei, Taiwan

Company

hirify.global develops secure silicon, systems, and AI-driven infrastructure based on its Trusted Control/Compute Unit technology.

What you will do

  • Define the end-to-end architecture for MLOps, agentic AI, and model optimization across edge devices.
  • Design data processing, versioning, CI/CD, human-in-the-loop, and active-learning pipelines.
  • Build lightweight on-device monitoring for operational metrics, inference quality, and concept drift.
  • Develop autonomous agents for resource-constrained edge devices using log analysis, computer vision, and open-source system tools.
  • Implement model security and verification, including secure protocols, authentication, model signing, entity verification, and injection prevention.
  • Collaborate with silicon and RTL teams and optimize models for custom NPU and FPGA inference through graph- and operator-level techniques.

Requirements

  • 8–10+ years of hands-on machine learning experience at senior or staff individual-contributor level.
  • Expert Python programming and deep experience with PyTorch or TensorFlow.
  • Strong understanding of modern ML algorithms, including Transformers.
  • Knowledge of computer architecture, digital logic, and RTL development with Verilog or VHDL.
  • Experience building complete MLOps lifecycles, developing LLM-based agentic systems, and working with log analysis or computer vision.
  • Hands-on experience with on-device model security, secure communication protocols, and hardware-aware optimization for NPUs or GPUs.

Nice to have

  • Experience with Apache TVM or MLIR.
  • Experience with Kubernetes, Kubeflow, Argo, or GPU scheduling platforms such as Run:AI.
  • Embedded development with C++, Rust, or Yocto, and familiarity with RISC-V.
  • Experience with AWS, GCP, or Azure.

Culture & Benefits

  • Work in a diverse environment focused on curiosity, execution, respect, and continuous learning.
  • Collaborate on real-world security and reliability problems across AI, silicon, and infrastructure.
  • Join a growing organization with more than 150 employees and commercial programs with Tier 1 industry leaders.

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 →