Computer Vision Engineer

Ocean Aero Inc
Gulfport, MS, United States
about 1 month ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Experienced
Experience required
3 years minimum
Working hours
Regular working hours
Job source

Tech stack

Computer Vision C++ (Programming Language) Command-Line Interface Nvidia CUDA Linux Hardware-In-The-Loop Simulation Python (Programming Language) Machine Learning Object Detection Software Engineering Systems Integration Robot Operating System
+4 more
Gaussian Information Technology ONNX (Open Neural Network Exchange) Format TensorRT

Job description

The Computer Vision Engineer will be responsible for designing, developing, integrating, and documenting computer vision capabilities for Ocean Aero’s autonomous vehicle perception, mapping, localization, and mission-decision systems. The role will focus on EO/IR sensing, Gaussian Splatting and 3D scene reconstruction, visual mapping and localization, occupancy matrix generation, and mapping camera observations to vehicle actions across surface and subsurface operations. The Computer Vision Engineer will be working alongside a team of creative engineers with a diverse set of backgrounds and skills. This role will report to the Chief Technology Officer.

Role Responsibilities:

  • Design and implement computer vision capabilities for EO/IR imagery across surface and subsurface missions
  • Build perception pipelines for camera calibration, image/video ingestion, detection, tracking, segmentation, and scene understanding
  • Develop visual mapping and localization tools, including occupancy matrices, georeferenced perception layers, and uncertainty outputs
  • Create 3D scene-reconstruction capabilities using Gaussian Splatting, multi-view geometry, photogrammetry, and related methods
  • Map camera observations to autonomy actions, mission recommendations, alerts, and decision-support outputs
  • Integrate camera, navigation, telemetry, and payload data across vehicle, edge, cloud, and customer systems
  • Validate perception behavior in simulation, hardware-in-the-loop, recorded datasets, and field environments
  • Collaborate across software, autonomy, vehicle systems, payload, and operations teams on build/test demonstrations
  • Create perception metrics, improve model performance, and maintain technical documentation

Requirements

  • B.S. from an accredited university, such as Computer Science, Software Engineering, Mathematics or Physics
  • Demonstrated 3+ years’ experience in software development/engineering
  • Strong foundation in computer vision, machine learning, geometry, and sensor processing, with proficiency in Python and C++ on Linux-based operating systems and command-line workflows
  • Hands-on experience with EO/IR imagery or video pipelines, including camera calibration, image enhancement, object detection, tracking, segmentation, or scene understanding
  • Experience developing visual mapping and localization capabilities from camera data, including occupancy matrices, SLAM/visual odometry, geospatial registration, or uncertainty-aware perception outputs
  • Experience building, testing, and documenting perception software using recorded datasets, simulation, field data, metrics, and automated validation tools
  • Excellent cross-department communication skills
  • Ability to think independently about creative solutions to design problems
  • Experience with sailing is a plus
  • Team player, with excellent verbal, written, and presentation skills
  • Ability to travel occasionally, as needed
  • US Citizenship required
  • Ability to obtain and maintain a US Department of Defense (DoD) Security Clearance
  • Possess a valid Transportation Worker Identity Credential (TWIC) or successfully pass the requirements to obtain one
  • Ability to pass drug screen, background check, and motor vehicle screening

Role Preferences:

  • Experience with Gaussian Splatting, NeRFs, photogrammetry, dense reconstruction, or 3D scene representations for robotics
  • Experience with EO/IR sensor payloads, thermal imagery, sensor synchronization, timestamping, and camera-to-navigation calibration
  • Experience deploying perception models at the edge using CUDA, TensorRT, ONNX, ROS/ROS2, or similar tooling
  • Exposure to camera-to-action autonomy stacks, perception-to-planner handoff, behavior selection, or real-time robotics control loops
  • Experience with maritime perception challenges and marine systems, including ROVs, UUVs, USVs or sail boats, is a definite plus; general interest in robotics

Benefits & conditions

Pulled from the full job description

  • Referral program
  • Tuition reimbursement
  • 401(k)
  • Health insurance
  • Retirement plan
  • Paid time off
  • Vision insurance, * 401(k)
  • Dental insurance
  • Employee assistance program
  • Flexible schedule
  • Flexible spending account
  • Health insurance
  • Health savings account
  • Life insurance
  • Paid time off
  • Referral program
  • Retirement plan
  • Tuition reimbursement
  • Vision insurance

About the company

Ocean Aero is an award-winning US company that has created the world’s first and only environmentally powered Autonomous Underwater and Surface Vehicle (AUSV.) Ocean Aero’s autonomous marine robot, the Triton, operates exclusively on wind and solar energy and performs long endurance missions on the ocean surface with the ability to dive below the waves for underwater operations. The Triton uses a complex array of custom-built sensors, marinized electronics and software systems to operate, sense and communicate in the environment.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.indeed.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

52 sec

Running persistent Linux environments directly on Windows

Ben Breard Ben Breard · WWC 2025

1:43 min

Mitigating vision classifier attacks using Gaussian blur techniques

David vonThenen David vonThenen · WWC 2025

4:52 min

Essential phases in building and refining language models

Anshul Jindal Anshul Jindal +1 · WWC 2025

10:40 min

Evaluating automotive software architectures and backend technologies

Georg Kühberger +1 · LIVE

2:39 min

Experiencing core Linux capabilities for DevOps administration

Michael Cade · LIVE

4:52 min

Envisioning a day in the life of future engineers

Raz Cohen · LIVE

Videos

See all

Related articles

See all