Build production Python inference services as an Applied AI Engineer Intern at Plusgrade, working with FastAPI and strict latency SLAs.

This fixed-term co-op pairs you with a senior mentor while supporting live machine learning services across Plusgrade’s partner ecosystem. You will develop web services, cloud infrastructure, pipelines, caching layers, and tests. The work focuses on model inference logic, contracts, and reliable production delivery.

Key Responsibilities:

- Build and operate real-time production inference services
- Write low-latency Python services with FastAPI
- Configure AWS cloud infrastructure for live systems
- Develop pipelines and caching layers for quick responses
- Write endpoint logic, unit tests, and integration tests

Requirements:

- Ability to navigate unfamiliar codebases and complex architectures
- Clean, readable Python development skills
- Understanding of FastAPI web services and model inference
- Knowledge of input, output, and latency constraints
- Comfort with Git, terminals, AWS, containers, streaming, or caching

Apply Python, FastAPI, testing, and cloud infrastructure skills to live AI inference services at Plusgrade.

#J-18808-Ljbffr

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