Edge AI Intern, Summer 2026

RBC • Orlando, FL

1d

About The Position

RBC is leveraging Artificial Intelligence to transform the future of banking. As an Edge AI Intern, you will join a specialized team within RBC SA&I (Solution Acceleration & Innovation) focused on moving high-performance AI models from the cloud to the edge. This position is ideal for an "Edge AI Expert" in the making—someone deeply interested in model compression, low-latency inference, and privacy-preserving AI architectures. You will help solve critical challenges in running Large Language Models (LLMs) and computer vision models on resource-constrained devices to ensure client data remains secure and local.

Requirements

• Currently enrolled in a Master’s program or advanced Undergraduate in Computer Science, Electrical Engineering, or a related field.
• Strong proficiency in Python and C++ (specifically for high-performance inference).
• Deep understanding of deep learning frameworks (PyTorch or TensorFlow) and their internal mechanics.
• Experience with model compression techniques (Quantization, LoRA, etc.).
• Familiarity with edge inference runtimes (e.g., ONNX, TensorRT, CoreML, or TFLite).

Nice To Haves

• Research experience or publications in efficient deep learning or systems for ML.
• Experience with LLM inference optimization (e.g., vLLM, llama.cpp).
• Knowledge of hardware-software co-design (understanding how memory hierarchy affects AI performance).
• Previous exposure to the financial industry or privacy-preserving technologies (e.g., Federated Learning).

Responsibilities

• Model Optimization: Research and implement techniques to compress state-of-the-art models (LLMs, CNNs) for edge deployment, utilizing methods such as quantization (INT8, INT4), pruning, and knowledge distillation.
• On-Device Deployment: Prototype and deploy inference engines on local hardware (e.g., mobile CPUs/NPUs, edge servers, or embedded systems) using frameworks like ONNX Runtime, TensorFlow Lite, or ExecuTorch.
• Latency Reduction: Analyze and profile model performance to identify bottlenecks; optimize inference pipelines for real-time financial applications (e.g., fraud detection, biometric authentication).
• Model Partitioning: Experiment with split computing strategies to intelligently divide workload between the edge device and the cloud, balancing bandwidth constraints with computational power.
• Benchmarking: Develop rigorous testing suites to measure power consumption, memory footprint, and inference speed across different hardware targets.

Benefits

• Impact: Work on "0-to-1" projects where your code could eventually run on the devices of millions of RBC clients.
• Mentorship: Direct access to RBC SA&I researchers and engineers who are deep experts in Edge AI architectures and modelling.
• Community: Participation in the RBC Student Program, including hackathons, executive networking, and technical "lunch and learns."
• The expected salary range for this position is ($30 per hour), depending on your experience, skills, and registration status, market conditions and business needs.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern