Назад
Company hidden
13 дней назад

Perception Lead (Computer Vision)

133 500 - 187 000$
Формат работы
onsite
Тип работы
fulltime
Грейд
lead
Английский
b2
Страна
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
Perception Lead (Computer Vision): Building and leading the perception stack for unmanned aircraft, covering detection, recognition, and image-space target tracking with an accent on degraded outdoor conditions, embedded deployment, and the transition from classical computer vision to learned models. Focus on defining perception architecture and evaluation, optimizing neural networks for constrained onboard compute, and maintaining reliable tracking through low light, thermal imaging, clutter, occlusion, and communications loss.

Location: Torrance, California, United States

Salary: $133,500–$187,000 USD per year base salary, with equity grants considered part of total compensation.

Company

hirify.global is a defense technology startup designing and manufacturing high-performance unmanned systems for modern battlefield operations.

What you will do

  • Own the architecture, roadmap, and delivery of a configurable perception stack across all unmanned aircraft platforms.
  • Lead and grow a small perception engineering team through hiring, mentorship, and technical reviews while contributing hands-on to the software.
  • Deliver detection, recognition, and image-space tracking that maintains and reacquires targets in clutter, glare, low light, occlusion, thermal imagery, and degraded communication conditions.
  • Define perception output contracts, calibrated confidence, degraded-detection signaling, and operating points with state estimation and engagement authorization owners.
  • Guide the transition from classical computer vision to learned detection and classification while retaining deterministic fallbacks and rigorous regression evaluation.
  • Deploy and optimize perception software on constrained onboard compute, including embedded accelerators and end-to-end latency budgets.

Requirements

  • 6+ years developing production computer vision or perception software, including 2+ years leading a team or technical program while remaining hands-on.
  • Experience delivering perception software on physical systems operating in uncontrolled outdoor environments, such as unmanned aircraft, robotics, autonomous vehicles, or aerospace platforms.
  • Expert proficiency in C++ and Python with production experience under real-time or resource-constrained requirements.
  • Strong knowledge of classical and learned perception, including tracking, feature matching, data association, detection, and classification networks.
  • Experience deploying neural networks to embedded accelerators such as NVIDIA Jetson, TensorRT, Qualcomm, or Hailo, including quantization and accuracy/latency characterization.
  • Experience with EO and IR/thermal imaging, camera calibration, small-object detection, perception evaluation, sensor synchronization, coordinate frames, and uncertainty representation.

Nice to have

  • Experience selecting and integrating thermal/LWIR sensors and managing their imaging and procurement trade-offs.
  • Experience building fleet data engines for log capture, indexing, dataset versioning, labeling, and model training.
  • Working familiarity with state estimation and sensor fusion, including visual-inertial odometry or Kalman filtering.
  • Experience with flight or field test operations, instrumented test articles, range operations, and log recovery.

Culture & Benefits

  • Fast-paced, hands-on startup environment focused on moving systems from design to deployment.
  • Work on unmanned systems tested in combat and built for large-scale production.
  • Competitive equity grants as part of the total compensation package.
  • Equal opportunity employment without regard to protected characteristics.

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 →