AR Vision Engineer – Photon‑Efficient CV/ML & SLAM

Snap; Greater London; Presencial; GBP 120.000 - 160.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Paid parental leave

Comprehensive medical coverage

Emotional and mental health support

Descripción de la vacante

Snap Inc. is looking for a seasoned researcher to advance computer vision and machine learning for photon‑driven imaging in our Spectacles AR platform. You will design and deploy models, work on tracking, depth estimation, SLAM, and novel imaging features for next‑generation AR glasses.

You will collaborate with a world‑class CV team to push the boundaries of detection and perception in wearable computing, applying state‑of‑the‑art ML techniques to real‑world imaging data.

Formación

• Strong foundation in photon‑efficient, event‑driven imaging systems is required.
• Solid background in computer vision, ML, and statistical signal processing.
• Deep understanding of 3D geometry, probability, statistics, and linear algebra.

Responsabilidades

• Design, train, and deploy ML models and CV algorithms for photon‑efficient imaging.
• Contribute to tracking, depth estimation, and SLAM systems using event‑driven data.
• Develop novel imaging features for AR glasses.
• Research ML/probabilistic techniques to improve speed and accuracy.
• Collaborate with CV team on next‑gen face, hand, and body tracking tech.

Conocimientos

C++

Python

PyTorch

TensorFlow

Computer Vision

Machine Learning

SLAM

VIO

Code quality

Educación

Bachelor's degree in a technical field

Master's degree in a technical field

PhD in a relevant technical field

Herramientas

PyTorch

TensorFlow

3D geometry

Descripción del empleo

Snap Inc. is looking for a seasoned researcher to advance computer vision and machine learning for photon‑driven imaging in our Spectacles AR platform. You will design and deploy models, work on tracking, depth estimation, SLAM, and novel imaging features for next‑generation AR glasses.

You will collaborate with a world‑class CV team to push the boundaries of detection and perception in wearable computing, applying state‑of‑the‑art ML techniques to real‑world imaging data.