Location:

Ottawa, Ontario (On-site at the Ottawa facility with periodic hybrid work options available) Position Type:

Full-Time Compensation:

Salary & Stock Options Benefits:

Comprehensive Health & Dental package, starting 3 weeks paid annual leave Contact:

If you have issues with your application, please email

[email protected]

About Obruta Founded in 2019, Obruta Space Solutions is enabling the in-space economy by developing the advanced autonomy systems required for in-orbit satellite servicing, logistics, and active debris removal. Today’s satellites are single-use assets that cannot be refueled, inspected, or repaired. Obruta is eliminating this barrier with our flagship product: the

RPOD Kit

—a turnkey, vision-guided Guidance, Navigation, and Control (GNC) subsystem that makes autonomous spacecraft docking commonplace.

Backed by leading venture capital and top-tier space innovation programs, Obruta is executing cutting-edge perception and navigation projects with the Canadian Space Agency (CSA), National Research Council (NRC), and international commercial partners.

The Role Obruta is seeking a specialized

Embedded Perception & Edge AI Engineer

to bridge the gap between bleeding-edge computer vision research and real-time flight deployment on embedded edge hardware.

In this role, you will take cutting-edge optical and neuromorphic (event-based) vision algorithms—developed in research frameworks like PyTorch—and transform them into ultra-fast, deterministic, CUDA-accelerated C++ pipelines running on onboard NVIDIA Jetson flight computers . You will optimize asynchronous event-stream processing, implement zero-copy memory architectures, build TensorRT inference engines, and minimize end-to-end latency from pixel trigger to GNC state estimation.

Long-term, you will be the core performance architect ensuring all of Obruta's multi-camera perception pipelines execute reliably within strict spacecraft Size, Weight, Power, and Cost (SWaP-C) constraints.

Key Responsibilities





Edge AI & High-Performance Perception Pipelines:

Design, optimize, and deploy real-time perception software pipelines in modern C++ and CUDA running on embedded Linux and NVIDIA Jetson compute modules.

Event-Camera Pipeline Optimization:

Translate asynchronous computer vision algorithms, spatio-temporal noise filters, and feature extractors into highly optimized, multithreaded implementations capable of processing massive event streams without data saturation.

Deep Learning Acceleration:

Quantize, optimize, and deploy neural network models for 3D vision and 6-Degrees of Freedom (DOF) pose estimation using NVIDIA TensorRT, ONNX Runtime, and custom CUDA kernels.

Low-Latency Architecture & Zero-Copy Pipelines:

Architect zero-copy shared memory frameworks and IPC mechanisms to seamlessly stream high-bandwidth camera data between perception front-ends, Extended Kalman Filters, and the core GNC flight stack.

Profiling & Hardware Resource Management:

Profile CPU/GPU load, thermal performance, and memory consumption on flight-representative compute boards to guarantee real-time deterministic execution under worst-case operational loads.

Hardware-in-the-Loop (HITL) Integration:

Collaborate with laboratory engineers and embedded developers to benchmark vision latency and throughput on physical testbeds in our dual-arm robotics laboratory.

Required Qualifications

Bachelor's or Master's degree in Computer Engineering, Computer Science, Electrical Engineering, Robotics, or a related discipline.

2+ years of professional experience

in embedded computer vision, or edge AI acceleration.

Robust proficiency in

modern C++

and parallel computing using

NVIDIA CUDA

.

Hands‑on experience deploying and profiling deep learning models on embedded hardware using

TensorRT

, ONNX Runtime, or OpenCV CUDA modules.

Solid understanding of Linux systems programming, multithreading, POSIX concurrency, and memory management.

Applicants must be legally authorized to work in Canada. Successful candidates must able to obtain and maintain a security assessment under the Controlled Goods Pro

📌 Embedded Perception (Ahuntsic)
🏢 Obruta Space Solutions
📍 Ahuntsic