Permanent Position – Toronto
About the Company
Riskfuel is pioneering the use of deep neural networks to accelerate the proprietary financial models used to calculate the values and the risk sensitivities of the financial instruments held by capital markets and insurance firms. Given the size of these portfolios and the many different risk sensitivities required, these models are run in large, overnight batch processes spread over thousands of servers. Riskfuel dramatically accelerates the process by constructing functionally equivalent models using DNNs. The Riskfuel models are a million times faster so that what once took all night to run can now be completed in seconds. With Riskfuel models, you get real-time valuation and risk management … and a massive reduction in the compute workload, saving money and reducing the firm’s environmental footprint.
We are doing exciting cutting-edge research and our technology is winning major industry awards. The work is varied, interesting and fast paced, with lots of opportunity for you to make impactful contributions. We are looking for talented individuals to work and learn alongside colleagues who are leaders in the field.
See more at our website Riskfuel.com.
About the Position
At Riskfuel, we work with big numbers. We run the client’s slow financial pricing models millions of times to generate the training data that we need for training our neural networks. The result is a training dataset that is used to teach DNNs how to approximate the client’s models very accurately and very quickly. Since we don’t want the training data generation to take years, we exploit techniques like load distribution across multiple nodes, micro-services, and event-driven architectures – every millisecond counts.
Here are some of the things you would be working on:
- Designing and training deep neural nets for equity derivatives models
- Understanding clients’ models used in valuation of traded derivatives products and insurance contracts
- Performing model validation of customer models over the training domain
- Creating dataset generation strategies, considering the statistical distribution of input values and the downstream effects on ML training results
- Designing and developing scalable workflows that can handle hundreds of millions of datapoints
- Adding new features around our machine learning code, including new network architectures, data strategies, etc
- Performance profiling and optimization
About the Candidate
- Has 2-5 years of experience in model validation or risk management of equity derivatives models
- Is proficient in Python or C++ with experience using PyTorch or TensorFlow
- Has a post-graduate degree in a STEM field (math, physics, actuarial science, or similar) with a deep understanding of numerical methods and stochastic processes
How to Apply
To apply to this position, please provide a resume and any additional information that you feel demonstrates your experience. We look forward to meeting you!