Top Computer Vision Jobs in Los Angeles, CA

Architect and deploy computer vision and perception systems for space-based missile defense. Develop C++ multi-band EO/IR image processing, physics-based feature extraction, object detection, tracking, and discrimination algorithms. Model infrared phenomenology, validate algorithms through high-fidelity software- and hardware-in-the-loop simulations, perform statistical performance analysis, and integrate reliable flight software for space-qualified processors.

Develop and optimize computer vision and machine learning perception algorithms for autonomous detection, classification, and pose estimation of space targets. Responsibilities include model training, evaluation, deployment to resource-constrained systems, simulation integration, sensor modeling, tooling maintenance, and collaboration across autonomy and mission software teams.

Develop, train, deploy, and maintain deep learning models and machine learning pipelines for electro-optical and infrared image processing. Build computer vision solutions involving object detection, image segmentation, and tracking; support rapid prototyping and operational integration. Collaborate with AI and engineering teams, troubleshoot systems, evaluate emerging ML techniques, and maintain production software. The role requires advanced machine learning expertise, strong mathematics, Python proficiency, deep learning library experience, and eligibility for a U.S. Government security clearance.

Develop, test, deploy, and maintain deep learning computer vision models for space and missile warning applications. Build sensor fusion and target tracking solutions, optimize real-time systems with GPU programming, and contribute to embedded systems and fire control architectures using Python, C, C++, and Rust. Collaborate with multidisciplinary teams to deliver mission-critical AI capabilities.

Develop computer vision and machine learning algorithms for autonomous spacecraft to detect, classify, and track orbital objects. Build sensor-processing pipelines, curate datasets, integrate perception software with ROS and simulation tools, and implement Python and C++ systems on Linux. Collaborate with autonomy, GNC, and flight software teams to define interfaces and reliability requirements for real-time, safety-critical onboard perception.

Develops end-to-end computer vision and perception software for unmanned aircraft, including target detection, classification, tracking, aimpoint selection, EO/IR imagery, and embedded deployment. Owns accuracy-latency tradeoffs, evaluation against flight data, sensor integration, regression testing, and perception interfaces. Provides senior technical design and code review while supporting mission-critical target discrimination and operator-authorized engagement workflows.

Develops advanced computer vision and image-processing algorithms for space situational awareness and astronomy applications. Responsibilities include researching SDA/SSA and photometry techniques, training and customizing machine-learning models, managing image-processing pipelines from sensor readout through cloud publication, generating simulated data, validating algorithms, and leading multidisciplinary research projects. The role also requires communicating technical findings to technical and non-technical stakeholders.

Lead computer vision model development and deployment, architect scalable pipelines, integrate hardware with AI monitoring, and ensure efficient manufacturing processes.

Researches, designs, develops, trains, and deploys computer vision and machine learning models. Builds and maintains ML software, testing and validation processes, and documentation. Applies image and video processing, deep learning, and computer vision techniques across edge and cloud-based platforms while improving existing applications and performance.

Develop and productize autonomous-driving perception software. Responsibilities include full SDLC execution, writing and testing C++ and Python code, integrating perception components, creating verification plans, deploying deep-learning models to embedded platforms, debugging systems, and evaluating performance with real and synthetic data.