Machine Learning Resident - Client: Blue Raven; term

Position: Machine Learning Resident - Client: Blue Raven (1 year term)
“If you are interested in the application of machine learning and signal processing for real-time fraud detection, this is the right opportunity for you. You will be part of a team of research and machine learning scientists building production-ready fraud detection systems from the ground up and will receive mentorship from experienced researchers and practitioners in the field.”

- Mara Cairo, Product Owner, Advanced Technology

Description
About the Role
This is a paid residency that will be undertaken over a 12-month period with the intention to be hired by our client, Blue Raven, afterwards (note: at the discretion of the client). The Resident will report to an Amii Scientist and regularly consult with the client team to share insights and engage in knowledge transfer activities. Successful candidates will be members of a cross‑functional project team with backgrounds in ML research, project management, software engineering, and new product development.

This is a rare opportunity to be mentored by world‑class scientists and to develop something truly impactful.

About the Client
Blue Raven is a well‑funded Canadian startup operating in stealth mode and focused on applying advanced AI techniques to the detection and prevention of financial fraud. The company is building an AI‑native platform designed to operate in real‑time, with a strong emphasis on accuracy, reliability, and continuous learning. Blue Raven has validated market demand and developed a working proof of concept, and is now transitioning from early technical validation to scaled product development.

The team is intentionally small, highly technical, and focused on building durable IP at the intersection of applied machine learning and real‑world fraud prevention.

Blue Raven’s founding team has a track record of building successful startups from the ground up. Brian Heath, a 3‑time founder with multiple successful exits and 13 patents, brings deep expertise in building products that scale. Rob Fraser, our technical leader, brings 26 years of hands‑on development experience and over a decade of engineering leadership.

About the Project
This project focuses on advancing an AI‑driven financial fraud detection system by transforming an existing decision‑management framework into a continuously learning model. The work emphasizes improving classification accuracy, reducing false positives and false negatives, and designing learning algorithms that adapt over time with human oversight. The project will involve assessing and prioritizing AI modeling opportunities, improving data labeling and evaluation practices, and documenting scalable approaches to learning‑based fraud detection across audio and text modalities.

The outcome is a robust, production‑oriented learning system that balances accuracy, performance, and reliability while remaining adaptable to evolving fraud patterns.

Required Skills / Expertise
Are you passionate about building great solutions? You’ll be presented with opportunities to both personally and professionally develop as you build your career. We’re looking for a talented and enthusiastic individual with a solid background in machine learning, particularly in building systems that combine audio signals and text transcripts to detect fraud in real time. You will help extend an existing fraud detection system by implementing agentic workflows, improving false‑positive evaluation and mitigation, and enabling the system to learn over time with human oversight.

Key Responsibilities

Design, implement, optimize, and evaluate self‑updating multimodal architectures for real‑time fraud detection. Develop and manage active learning pipelines utilizing uncertainty quantification and Human‑in‑the‑Loop (HITL) feedback to capture and adapt to continuous acoustic and semantic concept drift.

Prepare, curate, and preprocess high‑quality datasets for training or fine‑tuning, and validating models.

Utilize state‑of‑the‑art machine learning techniques and ML frameworks, tools and open‑source libraries to enhance model performance, accelerate workflows, and optimize data processing.

Undertake applied research on ML and fraud detection techniques…