Senior Data Scientist - Computer Vision & ML, Cross-Domain AI

AST SpaceMobile•Lanham, MD

2d•Remote

About The Position

AST SpaceMobile is building the first and only global cellular broadband network in space to operate directly with standard, unmodified mobile devices based on our extensive IP and patent portfolio and designed for both commercial and government applications. Our engineers and space scientists are on a mission to eliminate the connectivity gaps faced by today’s five billion mobile subscribers and finally bring broadband to the billions who remain unconnected. Position Overview We are seeking a Senior Data Scientist – Computer Vision & Video Machine Learning to design, develop, and deploy advanced visual AI solutions across a complex physical and operational environment. This role focuses on building production‑grade computer vision and video machine learning systems that enable automated inspection, physical‑world understanding, and vision‑guided robotics. The ideal candidate brings deep expertise in modern CV and video ML architecture, strong data science fundamentals, and disciplined MLOps practices to deliver scalable, reliable, real‑world visual intelligence systems.

Requirements

Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, Robotics, Machine Learning, Statistics, or a related quantitative field
Equivalent professional experience will be considered
A minimum of 6 years of experience in data science or machine learning
At least 3 years of hands‑on experience focused on computer vision and/or video machine learning with production deployments
Strong interpersonal skills and ability to collaborate effectively within cross‑functional teams
Excellent written and verbal communication skills, including executive‑level presentations
Meticulous attention to detail to ensure accuracy, reproducibility, and reliability of models
Strong problem‑solving and analytical thinking skills
Ability to operate effectively in fast‑paced, ambiguous environments
Ownership mindset with a focus on delivering production‑ready solutions
Python machine learning and computer vision frameworks (e.g., PyTorch, TensorFlow, OpenCV)
Deep learning architectures for vision and video (object detection, segmentation, temporal modeling)
MLOps and experiment tracking tools (e.g., MLflow, Weights & Biases, CI/CD for ML)
Data annotation and dataset management tools
SQL and data pipelines for large‑scale unstructured visual data
Edge and cloud deployment technologies for ML inference
Ability to work in a standard office or remote environment
Ability to use a computer and multiple monitors for extended periods
Ability to participate in meetings, design reviews, and collaborative working sessions

Nice To Haves

Experience with visual inspection, industrial quality systems, or automated perception pipelines
Background in robotic perception, manipulation, or autonomous system development
Experience with video‑based imitation learning or learning from demonstration
Exposure to complex physical systems, regulated environments, or safety‑critical applications
Advanced degree (PhD) with applied research in computer vision, video ML, robotics, or related fields
Experience with generative models for synthetic data generation or anomaly detection

Responsibilities

Design, train, and deploy computer vision and video ML models for automated visual inspection, diagnostics, and physical‑world analysis
Develop video understanding and temporal ML pipelines for learning physical procedures and enabling vision‑guided automation
Build perception models that allow automated and robotic systems to recognize objects, understand spatial context, and track task execution
Develop object detection, semantic segmentation, classification, and anomaly detection models across still imagery and video streams
Implement robust data cleaning and preparation workflows for image and video datasets, addressing noise, lighting variation, calibration drift, temporal alignment, and class imbalance
Design state‑space and feature representations for vision‑guided reinforcement learning agents and adaptive control systems
Develop recursive and online training pipelines that continuously improve models using production feedback and newly collected data
Apply physics‑informed ML constraints where visual patterns correlate with underlying physical processes
Implement MLOps best practices including experiment tracking, model versioning, automated validation pipelines, model registry management, and production monitoring
Collaborate with engineering teams to optimize vision model inference for deployment on edge devices, embedded systems, and cloud infrastructure
Manage large‑scale image and video annotation pipelines in partnership with domain experts
Communicate model performance, system impact, and insights through clear, executive‑facing analytics and visualizations