Information & Sensor Fusion Engineer

Preferred

Location:

Ottawa

Reports to:

CTO

Type:
Full-Time

Dominion Dynamics is building Canada’s first modern defence prime: software‑defined, attritable, and sovereign. We believe tomorrow’s military power won’t hinge on exquisite platforms, but on the seamless coordination of adaptable, AI‑driven capabilities across every domain. We’re building that family of systems, fielded with operators, sovereign by design, and accountable to Canada’s democratic values. We move fast, deploy with the CAF, especially in the Arctic, and operate with uncompromising respect for Canadian law, treaty obligations, and the CAF community.

High‑fidelity sensing and real‑time perception are the foundation of reliable, autonomous operations in remote and contested environments. This role closes the gap between experimental ML research and operational sensor fusion pipelines that must run deterministically at the edge; its output directly improves situational awareness, robustness, and mission effectiveness.

You will drive the development and deployment of sensor‑fusion and perception systems; from model development and real‑time inference to integration with edge compute and data pipelines. This role focuses on producing high‑performance, testable fusion stacks that deliver robust, explainable outputs under field conditions.

Note: This role includes a forward‑deployed mandate
. You’ll work hands‑on with deployed systems and operators in real‑world environments.

• Design, train, and validate sensor‑fusion models and perception pipelines using Python and frameworks such as PyTorch or Tensor Flow.
• Implement real‑time inference and optimization techniques suitable for edge compute and constrained hardware.
• Implement perception pipelines that combine Computer Vision (CV) with classical estimation; support visual pipelines using OpenCV, OpenGL/WebGL where appropriate.
• Build data ingestion, preprocessing, and labeling tooling for high‑throughput sensor streams.
• Implement unit/integration tests and continuous evaluation to detect model drift and performance regressions.
• Collaborate closely with embedded systems and mechanical teams to define interfaces and verify end‑to‑end behavior.
• Support field trials and on‑site model tuning; iterate rapidly based on deployment feedback.
• Document algorithms, performance baselines, and operational constraints for cross‑functional teams.

• Bachelor’s or Master’s in Computer Science, Electrical Engineering, Robotics, or equivalent practical experience.
• Senior level: 5+ years building and deploying ML models and sensor‑fusion systems in production or fielded environments.
• CV depth in one or more:
  Visual Odometry, SLAM, Multi‑view Geometry, Structure from Motion, Stereo Vision, RGB‑D, Camera Calibration, Photogrammetry.
• Strong proficiency in Python and hands‑on experience with PyTorch and/or Tensor Flow; working knowledge of OpenCV.
• Experience with data pipelines, labeling workflows, and model validation at scale.
• Practical experience optimizing models for edge inference and constrained compute.
• Comfortable collaborating with hardware teams and validating models against real sensor data.
• Pragmatic, low‑ego problem‑solver with experience supporting field deployments and debugging in operational settings.
• Eligibility for Canadian security clearance preferred;
  Canadian citizenship an asset.

At Dominion Dynamics, we’re designing systems that work where others fail, in the most extreme environments on Earth. We give you the chance to shape the future of Canada’s sovereign defence, build real capability with CAF and allies, move fast in small teams, operate with integrity under Canadian law, and have an impact from day one with equity, responsibility, and direct access to leadership.

Competitive salary and meaningful equity participation.

Seniority level:
Mid‑Senior level

Employment type:

Full‑time

Job function:
Information Technology

Industries:
Defense and Space Manufacturing

Referrals increase your chances of interviewing at Dominion Dynamics by 2x.