Machine Learning Scientist

Job summary

Research, design, and prototype deep learning architectures for large-scale industrial computer vision tasks, including detection, segmentation, and anomaly detection. Develop data strategies, evaluate and improve model performance, and document experiments and procedures to support reproducibility and engineering integration.

Job details

About DarkVision Technologies Inc. DarkVision is a Vancouver-based tech company that has been disrupting the industrial imaging market since 2013. We have created the world’s most advanced acoustic-based imaging platform, revolutionizing how our clients quantify and visualize the integrity of their critical assets. Backed by Blackstone, one of the world’s largest private equity firms, DarkVision’s team of Software, Mechanical, and Machine Learning Engineers and Data Analysts is rapidly expanding to meet the demand for the company’s current and upcoming products. Our employees work on cutting-edge technologies that blend science with real-world applications. We invite you to join our team for the exciting journey ahead as we become the global leader in industrial imaging. Your Job DarkVision is seeking a Machine Learning Scientist to join our Imaging & AI team. You will research, design, and prototype the deep learning architectures that power our automated analysis tools. You will solve complex computer vision challenges to enable interpretation of industrial data at scale. DarkVision’s ultrasound imaging system collects huge datasets on the order of terabytes, detecting sub-millimetric defects in industrial assets that span hundreds of kilometers. It is essential that we develop algorithms for the automated processing, classification, and visualization of this data. As a Machine Learning Scientist, you will focus on the mathematical and architectural challenges of interpreting this data, and creating models that learn efficient and generalizable representations for real-world industrial applications. This role is on-site at our North Vancouver, BC HQ, where employees enjoy a wide array of amenities including a fully equipped gym, squash court, steam room, climbing wall, and more! Our Team Working in the Imaging & AI team, you will join a multidisciplinary group of scientists and engineers. This team is responsible for early-stage ideation, research, experimentation, and development. You will collaborate closely with other technical members to ensure our models are integrated seamlessly into our products. What You Will Do Applied Research & Architecture Design: Research and develop state-of-the-art deep learning architectures to solve large-scale industrial problems. You will target tasks such as object detection, instance segmentation, semantic segmentation, and anomaly detection. Model Prototyping: Rapidly prototype and validate new model concepts using Python and deep learning frameworks. You will own the experimental phase, ensuring models are statistically valid and effective before collaboration with engineering. Data Strategy: Work closely with Data Analysts and Data Scientists to explore and organize datasets. You will define the data extraction and preprocessing strategies required to train robust models. Performance Optimization: Continuously monitor model success metrics and research improvements to increase model robustness and accuracy on challenging, real-world data Documentation & Knowledge Transfer: Document model architectures, training details, and dataset procedures to ensure reproducibility, and facilitate smooth integration by the engineering team. Who You Are (Basic Qualifications) Master’s degree in Computer Science, Electrical Engineering, or a related field; PhD preferred 3+ years of experience developing or researching deep learning models Proficiency in Python and deep learning frameworks such as PyTorch, JAX, etc. Ability to design experiments and interpret complex results What Will Put You Ahead Experience processing medical or industrial ultrasound images Publications in top-tier computer vision venues (e.g., CVPR, ICCV) Experience with self-supervised or unsupervised learning methodologies Hands-on experience with ML lifecycle management tools like MLFlow, Amazon SageMaker, GPC Vertex AI, etc. Hands-on experience with orchestration tools like Kubeflow, Prefect, Airflow, etc. Experience leading or mentoring other scientists or researchers Ability to work in a fast-paced, self-driven environment Excellent communication skills to present research findings and write technical reports General Salary Range For this role, we anticipate paying $100,000 to $150,000 per year. This role is eligible for variable pay, issued as a monetary bonus or in another form. keywords: ML, machine learning, AI, deep learning, DL, algorithm, development, model, training, applied research, experiment, supervised, unsupervised, computer vision, CV, image process, image analysis, ultrasound, U/S, ultrasonic, Python

What you’ll do

Research, design, and prototype deep learning architectures for large-scale industrial computer vision tasks, including detection, segmentation, and anomaly detection. Develop data strategies, evaluate and improve model performance, and document experiments and procedures to support reproducibility and engineering integration.

Requirements

A master's degree in computer science, electrical engineering, or a related field is required, with a PhD preferred, along with at least three years of experience developing or researching deep learning models. Candidates should be proficient in Python and deep learning frameworks such as PyTorch or JAX and be able to design experiments and interpret complex results.

Benefits

• Fully Equipped Gym
• Squash Court
• Steam Room
• Climbing Wall

Listed skills

• Technical Documentation · Preferred
• Python · Preferred

Other relevant skills

Identified from the job description. Confirm important requirements above.

• Deep Learning
• Computer Vision
• Python
• PyTorch
• JAX
• Object Detection
• Instance Segmentation
• Semantic Segmentation
• Anomaly Detection
• Experiment Design
• Ultrasound Image Processing
• Self-Supervised Learning
• Unsupervised Learning
• Model Optimization
• Data Preprocessing
• Technical Documentation

Job areas

• Technology
• Science & Research
• Data & Analytics
• Software
• Engineering

More jobs from DarkVision