B

Booz Allen

Builds AI and cyber systems for the US government

Computer Vision Software Engineer

Computer VisionConfirmed live in the last 24 hours
Full-timeDayton, OH, USA$69.3k - $158k /yrIn-person

About the Job

Requirements

  • At least 3 years of experience developing computer vision algorithms for detection, tracking, or sensor-based analytics in remote sensing or GEOINT-relevant environments.
  • At least 1 year of experience applying deep learning to computer vision problems using transformer-based, self-supervised, or contrastive learning architectures such as DINO, CLIP, or SAM.
  • Experience building pipelines in Python or C++ for algorithm development, training, evaluation, or deployment.
  • Experience with GPU-accelerated workflows.
  • Experience with classical tracking and estimation methods, such as Kalman or extended Kalman filters, supporting real-time development needs.
  • An active TS/SCI clearance and willingness to take a polygraph examination.
  • A bachelor's degree in a STEM field.

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 to support real-time algorithm development.
  • Contribute to GPU-accelerated model development using CUDA, RAPIDS, or vendor-provided inference runtimes.
  • Collaborate with multidisciplinary engineering teams to test, refine, and operationalize computer vision models for constrained-compute or real-time environments.
  • Support implementation of microservice-based inference pipelines or containerized model deployments under senior guidance.
  • Contribute to the architecture and implementation of novel single- and multi-sensor platform detection and tracking algorithms and track fusion of targets.

Desired Qualifications

  • Experience in GPU programming, including CUDA or RAPIDS.
  • Experience developing synthetic modeling of kinematic target features.
  • Experience with AI-augmented development workflows or agentic tools, such as Codex, Claude Code, OpenCode, or another multi-agent approach.
  • Knowledge of modern software design patterns, including microservice design and orchestration in Kubernetes deployment.
  • A master's degree in Computer Science, Electrical Engineering, Computer Engineering, AI/ML, Physics, Mathematics, or another related field.

About the Company

Booz Allen

Builds AI and cyber systems for the US government

Booz Allen builds and runs technology for the U.S. government, mostly for the military and intelligence agencies, and its engineers work alongside consultants who know each agency's mission. In 1958, it helped the U.S. Navy create PERT, a project-scheduling method first used on the Polaris submarine missile program and later adopted across government and industry. Its teams design cyber defenses, AI and data tools, and battlefield communications, and it sells its own products, such as Vellox, a suite of AI tools that spot and fight off hackers. Agencies pay mainly through multi-year contracts that reimburse costs, bill hours, or set a fixed price. Booz Allen was founded in 1914 and is based in McLean, Virginia.

Company size
10,001+
Company stage
IPO
Headquarters
McLean, VA
Founded
1914

Recently Posted Jobs

Explore more opportunities at Booz Allen

See more jobs