Computer Vision Engineer — Real-Time AI & Edge Models

United States Digital Space LLC; San Mateo (CA); On-site; USD 180,000 - 300,000; Full time

Benefits offered by this job

Healthcare coverage

Mental health support

Parental leave

Job summary

United States Digital Space LLC is seeking a Computer Vision Engineer to develop and deploy AI models for video analytics, including detection and recognition tasks. The role emphasizes building efficient C++ pipelines and integrating DL models into edge and cloud workflows.

You will work with PyTorch, TensorFlow, and Keras, prototyping algorithms for object and people detection, license plate recognition, and facial recognition, while maintaining scalable data structures and systems.

Qualifications

• Bachelor's degree in Computer Science (or related field) with research experience preferred.
• 1–3 years of industry software engineering experience.
• 1+ years of work or research experience with current neural net frameworks.
• Mastery of at least one practical programming language.
• Experience in an agile team software development environment.

Responsibilities

• Write clean, modular C++ code.
• Apply traditional computer vision algorithms.
• Train deep learning networks using PyTorch, TensorFlow, Keras, or similar.
• Design robust data structures and software architecture.
• Willingness to work onsite five days per week.

Skills

C++

Computer vision

Deep learning frameworks

PyTorch

TensorFlow

Keras

Data structures

Education

Bachelor's Degree in Computer Science

Tools

TensorFlow

PyTorch

Keras

Job description

United States Digital Space LLC is seeking a Computer Vision Engineer to develop and deploy AI models for video analytics, including detection and recognition tasks. The role emphasizes building efficient C++ pipelines and integrating DL models into edge and cloud workflows.

You will work with PyTorch, TensorFlow, and Keras, prototyping algorithms for object and people detection, license plate recognition, and facial recognition, while maintaining scalable data structures and systems.