Machine Learning Scientist

Your Job

DarkVision, part of Koch Engineered Solutions, is looking for a Machine Learning Scientist for a temporary position with a 1-year term. DarkVision’s ultrasound imaging asset inspection system collects huge datasets in the order of hundreds of gigabytes that are several kilometers long where a defect may be on the order of a few millimetres. It is essential that we develop algorithms for automated processing, measuring, classification, and visualization of this data since manual processing is both time consuming and inconsistent.

As a Machine Learning Scientist, you will be involved in researching, designing, and implementing deep learning architectures that learn efficient generalizable representations for several vision-based tasks. You will report to our Vice President of Research & Innovation and be responsible for developing machine learning pipelines for continuous training, evaluation, and deployment of deep learning models.

Our management process is light and generally milestone driven, using pseudo-Agile sprints derived from our quarterly and yearly goals. All goals are internally generated with plenty of room for feedback.

This is a temporary position with a 1-year term. It is on-site in our HQ in North Vancouver, BC.

Our Team

With the largest ultrasound datasets globally, DarkVision's Research & Innovation team unites top-tier PhDs, engineers, and research scientists to pioneer automated image processing and deep learning architectures.

What You Will Do

• Research: Rapid model prototyping, training, and deployment of state-of-the-art deep learning models to solve large-scale industrial problems. You will be investigating image classification, object detection, instance segmentation, semantic segmentation, anomaly detection, and other bespoke tasks for processing industrial ultrasonic array data.
• Pipeline: Work with our ML Ops team to build cloud-based pipelines for large-scale image pre-processing, data-augmentation, training, post-processing, and inference.
• Deploy: Work with the Software Development Team to deploy model in production for its end-users.
• Monitor: Continuously monitor success matrices of the assigned ML project and make continuous improvements for increasing model robustness and efficiency.
• Data Analysis: Work closely with our Data Analysts to explore, analyze, and organize data; perform data extraction and preprocessing for training and evaluation purposes.
• Document: Document model architecture, training details, dataset extraction, and cleaning procedures for reproducibility, product management, and internal training.

Opportunities to Learn

• Applying deep learning to real world industrial datasets containing billions of images.
• Exploration of the state-of-the-art methodologies in computer vision like self-supervised learning and unsupervised learning for the purpose of non-destructive testing.
• Exposure to full ML lifecycle and orchestration management tools like Prefect, Kubeflow, AWS SageMaker, Weights, and Biases.
• Converting ideas into intellectual property assets (e.g. patents).

Who You Are (Basic Qualifications)

• Experience developing and training deep learning models from scratch.
• Master’s degree in Computer Science, Computer Engineering, Electrical Engineering or a ML/AI related field; PhD preferred.
• Proficient in Python and at least one mainstream deep learning framework, such as PyTorch, TensorFlow, JAX, etc.

What Will Put You Ahead

• Experience with medical or industrial ultrasound images for deep learning-related projects.
• Experience in deep learning projects for industrial non-destructive testing.
• Experience leading and mentoring ML engineers and ML scientists.
• 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.
• Working knowledge of Git, Docker, and cloud services like AWS and GPC.
• Publications in top tier venues likes CVPR, ICCV, etc.
• Experience with Reinforcement Learning and/or Few-shot Learning
• Experience with NLP (Transformers, RNNs)
• Experience in self-supervised and/or unsupervised learning
• Experience with Generative Model / Diffusion
• Experience with Causal Inference
• Great communicator with excellent data presentation, and report writing skills.
• Be able to work in a fast-paced, self-driven environment.

General Salary Range

For this role, we anticipate paying $100,000 - $180,000 per year. This role is eligible for variable pay, issued as a monetary bonus or in another form.

At Koch companies, we are entrepreneurs. This means we openly challenge the status quo, find new ways to create value and get rewarded for our individual contributions. Any compensation range provided for a role is an estimate determined by available market data. The actual amount may be higher or lower than the range provided considering each candidate's knowledge, skills, abilities, and geographic location. If you have questions, please speak to your recruiter about the flexibility and detail of our compensation philosophy.

Who We Are

DarkVision Technologies Inc. is a Canada-based tech company disrupting the industrial imaging market since 2013. We have created the world’s most advanced acoustic-based imaging platform. We are packaging it into multiple new product lines, revolutionizing how our clients quantify and visualize the integrity of their critical assets.

Backed by Koch Industries, one of the world’s largest privately held companies, DarkVision’s team of Mechanical, Skunkworks, Electrical, Software, and Machine Learning Engineers is rapidly expanding to meet the demand for the company’s current and upcoming products.

We allow employees to 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.

At Koch, employees are empowered to do what they do best to make life better. Learn how our business philosophy helps employees unleash their potential while creating value for themselves and the company.

Additionally, everyone has individual work and personal needs. We seek to enable the best work environment that helps you and the business work together to produce superior results.

How To Apply

If you have the above qualifications, we would like to hear from you. We thank all applicants in advance, but please be advised that only those selected for an interview will be contacted.

We are an equal opportunity employer. If you require accommodation or assistance at any time during the application or selection processes, please submit a request by following the directions located in the FAQ section at the bottom of the kochcareers.com webpage.

Successful candidates will be required to complete a criminal background check.

Keywords: machine learning, ML, deep learning, DL, computer vision, imaging, image processing, reinforcement learning, few-shot learning, NLP, RNN, Transformers, self-supervised, unsupervised, generative model, diffusion, casual inference, ultrasound, ultrasonic, non-destructive testing, NDT, NDE, industrial, PyTorch, Tensorflow