Senior Computer Vision, Perception Engineer

Reqiva; Melbourne; In loco; AUD 150.000 - 210.000; Tempo pieno

Descrizione del lavoro

Reqiva is partnering with an ambitious Australian deep-tech business to recruit a Senior Perception, Computer Vision Engineer. You will own perception capability, developing, optimising and deploying CV models for autonomous systems on edge hardware.

You’ll work across AI/ML engineering, contribute to pipelines, datasets and evaluation frameworks, and collaborate with robotics and embedded teams to deliver production-ready solutions.

Competenze

• Degree in Computer Science, AI, Electrical Engineering, Robotics, or related field, or equivalent practical experience.
• 5+ years’ experience developing and deploying CV models into production.
• Strong knowledge of modern DL and CV including detection, segmentation, tracking and anomaly detection.
• Experience with PyTorch and/or TensorFlow.
• Strong understanding of classical CV including calibration, camera models, multi-view geometry.

Mansioni

• Develop and maintain a library of CV models for detection, surveillance, inspection, tracking and anomaly detection.
• Evaluate and optimise existing open-source models and develop bespoke solutions.
• Own and improve model optimisation pipelines (pruning, quantisation, inference).
• Develop automated testing to measure model accuracy, compute performance, power and thermal efficiency on target hardware.
• Deploy and optimise AI models on edge computing platforms under real-world constraints.
• Build and manage datasets with labelling, versioning, synthetic data and active learning workflows.
• Collaborate with robotics, embedded systems and hardware teams to integrate perception into autonomous platforms.
• Contribute to localization and navigation capabilities in GPS-denied environments (visual-inertial odometry, sensor fusion).
• Establish standards and best practices across CV, modeling, testing and deployment.

Conoscenze

PyTorch

TensorFlow

C++

Python

Edge AI

ROS/ROS2

CUDA

Model optimization

Embedded Linux

Formazione

Bachelor's degree in CS/EE/AI

Master’s or PhD preferred

Strumenti

NVIDIA Jetson

TensorRT

ONNX Runtime

GStreamer

DeepStream

Descrizione del lavoro

Senior Perception, Computer Vision Engineer

Type: Full-time, Permanent

About the opportunity

We are partnering with an innovative Australian deep-tech business developing next-generation autonomous systems and advanced AI technologies for complex real-world environments.

The business is working at the intersection of artificial intelligence, robotics, computer vision and edge computing, developing intelligent systems capable of operating in challenging and resource-constrained environments.

This is an opportunity to join an early-stage engineering team, working closely with the founding team and having a genuine influence on the technical direction and development of its products.

The role

We are looking for a Senior Computer Vision Engineer to take ownership of the perception and edge AI capability.

You will be responsible for developing, optimising and deploying computer vision models across autonomous and intelligent systems, taking solutions from research and experimentation through to real-world hardware deployment.

The role combines hands-on computer vision engineering, deep learning, model optimisation and embedded deployment. You'll have significant technical ownership, helping establish the engineering standards, tools and processes that will support the company's continued growth.

Key responsibilities

• Develop and maintain a library of computer vision models for applications including object detection, surveillance, inspection, tracking and anomaly detection.

• Evaluate, adapt and optimise existing open-source models, as well as develop bespoke solutions where required.

• Own and improve model optimisation pipelines, including pruning, quantisation and inference performance.

• Develop automated testing and evaluation frameworks to measure model accuracy, compute performance, power consumption and thermal efficiency on target hardware.

• Deploy and optimise AI models on edge computing platforms, working within real-world power, memory and processing constraints.

• Build and manage datasets, including data labelling, versioning, synthetic data generation and active learning workflows.

• Work closely with robotics, embedded systems and hardware engineering teams to integrate perception capabilities into autonomous platforms.

• Contribute to localisation and navigation capabilities in GPS-denied environments, including visual-inertial odometry and sensor fusion.

• Establish technical standards and best practices across computer vision, model development, testing and deployment.

• Help shape and grow the wider AI/ML engineering capability as the business scales.

About you

• Degree in Computer Science, Artificial Intelligence, Electrical Engineering, Robotics, Applied Mathematics or a related discipline, or equivalent practical experience.

• Typically 5+ years' experience developing and deploying computer vision models into production environments.

• Strong practical knowledge of modern deep learning and computer vision, including object detection, segmentation, tracking and anomaly detection.

• Experience with PyTorch and/or TensorFlow.

• Strong understanding of classical computer vision, including camera calibration, camera models, multi-view geometry and image processing.

• Hands-on experience optimising machine learning models, including quantisation, pruning and knowledge distillation.

• Experience deploying models using TensorRT, ONNX Runtime, OpenVINO or similar frameworks.

• Strong C++ and Python programming skills.

• Experience working with embedded Linux and edge computing hardware.

• Understanding of GPU acceleration and CUDA would be advantageous.

• A strong experimental and analytical mindset, with the ability to evaluate model performance and translate research into practical engineering solutions.

• Comfortable working in an early-stage engineering environment, taking ownership and collaborating across multidisciplinary teams.

Desirable experience

• Experience with autonomous systems, robotics, drones or other edge AI applications.

• Exposure to satellite imagery, thermal, multispectral or hyperspectral imaging.

• Experience with visual-inertial odometry, SLAM, UWB ranging or sensor fusion.

• Familiarity with ROS / ROS 2, NVIDIA Jetson, DeepStream or GStreamer.

• Experience with hardware acceleration platforms beyond NVIDIA, including Qualcomm, Hailo, Intel or FPGA.

• Synthetic data generation and simulation-to-real workflows.

• Experience deploying vision-language or open-vocabulary models on edge hardware.

• Background in defence, aerospace or other advanced technology environments.

• Master's or PhD in Computer Vision, Machine Learning or a related discipline.

The opportunity

• Join an ambitious Australian deep-tech business working on advanced AI, robotics and autonomous technologies.

• Take genuine ownership of computer vision and edge AI development.

• Work directly with experienced founders and multidisciplinary engineering teams.

• Influence architecture, technical direction and engineering standards.

• Develop technology from research and prototyping through to real-world deployment.

• Help shape and build an engineering function as the business grows.

Additional requirement: Australian citizenship is essential, with eligibility to obtain and maintain an Australian Government security clearance.