Perception Engineer - Defense (All-Domain)

About the role

The Perception Engineer role at Applied Intuition Defense is a hands-on, full-stack, high tempo position where you will be part of an expert team rapidly pursuing the second (99%) and third nine (99.9%) of perception model performance across maritime, land, air-to-surface, and surface-to-surface domains, in EO and IR.

We develop our own custom detector and classifier architectures, we’ve developed our own comprehensive MLOps tooling allowing us to rapidly iterate at the scale of millions of images and videos, we make our own industry-leading labeling software, and we manage in-house labeling on a daily basis. We do all of this using frontier AI and large token budgets. If something needs to be built to get the job done, we will build it. If you have extensive modeling experience with transformers, vision-language models, diffusion models, and video model training pipelines, we need you. If you have deployed production ML models into the real world or optimized them heavily, we need you.

At Applied Intuition Defense, you will:

• Develop perception models that find and classify targets with an error rate of <1/100

• Deploy perception models to Jetson Orin+ boards and optimize models for better-than-realtime performance.

• Build large foundation models for high-accuracy assisted data labeling.

• Build tooling across the entire perception stack: labeling tools, simulation.

• Work with the best and most competitive AI talent in the world through collaboration with Applied Intuition self-driving staff.

• Scale up datasets using a variety of state-of-the-art data generation techniques including simulation, diffusion, and generative AI.

• Create and maintain highly optimized models and inference software providing model results at maximum attainable frames per second (FPS) on Jetson-like hardware.

• Collaborate across the hardware, sensor, tracking, autonomy, and testing teams to ensure seamless deployment in on-site DoD testing and demonstration events.

We’re looking for someone who has:

• MS or PhD in Computer Engineering, Robotic Engineering, Computer Science, or equivalent OR 5+ years of relevant experience working with simulation, machine learning, and ML infrastructure.

• Proficiency in training ML models in PyTorch on multi-machine, multi-GPU systems.

• Experience in optimizing and deploying machine learning models to edge devices.

• Strong experience with agentic coding with proven experience in Python and/or cpp.

• Experience leveraging modern AI-powered development tools (e.g., GitHub Copilot, Cursor) to accelerate the creation of robust, well-tested systems.

• Adeptness with remote software development, the ability to handle and process large datasets, and a capacity to learn new software and algorithms as needed with little supervision .

Travel Requirements:

• Must be willing to travel as projects require, usually for SW/HW integration and/or demonstrations; estimated average travel is 2-5 days every other month (10-20%)

• Interested candidates should also inquire about relocation assistance to Applied Intuition Defense facilities near Destin, FL, Washington, D.C., or San Diego, CA

Security Requirements:

• Must be a U.S. Citizen

• Must hold or be eligible to obtain and maintain a U.S. security clearance

For more information about U.S. security clearances: click here.

Nice to have:

• PhD in Computer Vision, Machine Learning, or related field with strong academic contributions

• 5+ years of experience building and deploying perception models on real-world hardware

• A background in generating datasets using simulation engines like Unreal Engine, NVIDIA Omniverse, Blender, or 3D asset creation tools

• Experience with deeply optimizing Transformer-based models for edge devices like NVIDIA Jetson boards

• Familiarity with Software-in-the-Loop (SIL) and Hardware-in-the-Loop (HIL), including integration and test experience on common COTS hardware devices (e.g., NVIDIA Jetson, Raspberry Pi5)