Mid-Level Computer Vision Software Engineer

About the role

Booz Allen is looking for a Mid-Level Computer Vision Software Engineer in Dayton to join a mission-focused engineering team building computer vision, multi-sensor fusion and detection and tracking capabilities for remote sensing and GEOINT environments. You will design, implement and optimize CV algorithms and deep learning pipelines, working closely with senior engineers on well-defined parts of the technical solution.

Key responsibilities

• Develop and implement computer vision algorithms for target detection, characterization and tracking across single- and multi-sensor data
• Build and maintain model training, evaluation and deployment pipelines in Python or C++
• Apply deep learning approaches, including transformer-based architectures such as DINO, CLIP or SAM, to image understanding problems
• Integrate classical estimation methods, such as Kalman-family filters, with modern deep learning workflows for real-time algorithm development
• Contribute to GPU-accelerated model development using CUDA, RAPIDS or vendor-provided inference runtimes
• Work with multidisciplinary teams to test and refine models for constrained compute or real-time environments
• Support microservice-based inference pipelines or containerized model deployments under senior guidance
• Contribute to single and multi-sensor detection and tracking algorithms and target fusion

Required profile

• 3+ years of experience developing computer vision algorithms for detection, tracking or sensor-based analytics in remote sensing or GEOINT environments
• 1+ year of experience applying deep learning to CV problems with transformer-based, self-supervised or contrastive learning architectures (e.g., DINO, CLIP, SAM)
• Bachelor's degree in a STEM field; a Master's degree in CS, EE, CE, AI/ML, Physics or Mathematics is a plus
• Active TS/SCI clearance and willingness to take a polygraph exam

Required skills

• Pipelines in Python or C++ for algorithm development, training, evaluation or deployment
• GPU-accelerated workflows
• Classical tracking and estimation methods such as Kalman or extended Kalman filters
• Nice to have: CUDA or RAPIDS, synthetic modeling of kinematic target features, AI-augmented development tools, microservices and Kubernetes, and a Master's degree

What we offer

• Projected annual salary range of $69,300 to $158,000 depending on experience, education and contract specifics
• Health, life, disability, financial and retirement benefits, paid leave, professional development, tuition assistance and work-life programs
• Recognition awards for exceptional performance