Optimize AI inference for edge devices while applying coding, performance analysis, and software prototyping skills in an engineering internship.

This internship focuses on applied AI engineering across inference workflows and agentic architectures. You will analyze latency, memory usage, computational efficiency, and model performance while developing optimization approaches. The work also includes integrating AI models with edge hardware and documenting technical recommendations.

Key Responsibilities:

- Optimize AI inference workflows for edge-device environments
- Analyze latency, memory, efficiency, and model performance
- Identify bottlenecks in agentic AI architectures
- Develop and test software prototypes
- Document findings, designs, and performance recommendations

Requirements:

- Pursuing a bachelor's degree in a related technical discipline
- Knowledge of artificial intelligence and machine learning
- Experience with coding and software development
- Expertise in AI inference and performance optimization
- Understanding of agentic AI and edge computing

Apply analytical, prototyping, testing, and optimization capabilities to AI systems operating across edge environments.

📌 AI Inference Optimization Engineering Intern (Vancouver)
🏢 UEC
📍 Vancouver