Build low-latency Python inference services as an Applied AI Engineer Intern at Plusgrade in Toronto, working hybrid on real-time machine learning systems.

This fixed-term co-op role works with a senior mentor on production services serving Plusgrade’s partner ecosystem. You will develop with FastAPI, AWS, testing, and AI-assisted tools while supporting live systems under strict latency SLAs.

Key Responsibilities:

- Build production inference services serving machine learning models
- Write clean, low-latency Python services with FastAPI
- Configure AWS infrastructure and containerized deployments
- Build pipelines and caching layers for quick responses
- Write endpoint logic, unit tests, and integration tests

Requirements:

- Ability to navigate unfamiliar codebases and complex architectures
- Understanding of model inference logic and input-output contracts
- Knowledge of latency constraints and web service development
- Comfort with Git, terminal workflows, cloud infrastructure, and streaming
- Ability to audit AI-generated code for quality and reliability

Apply Python, FastAPI, AWS, testing, and engineering judgment to real-time inference services supporting Plusgrade’s partners.

#J-18808-Ljbffr

📌 Applied AI Python Engineer Intern (Toronto)
🏢 Plusgrade
📍 Toronto