CS2680 Modern AI Systems: Agents and System Optimizations
Computing setup

Assignment by assignment

Work Use Why
Assignment 1 Claude Code + AWS Build the web UI with the course agent account, and deploy it on EC2 if you want it reachable. No GPU required.
Assignment 2 and Assignment 3 Laptop/HPC + Harvard OpenAI/Gemini/Anthropic API The model runs behind a commercial API. Any machine is enough; use AWS or HPC job when the experiment should run for hours.
Assignment 4 HPC GPU (RTX PRO 6000 Blackwell) You serve the model yourself. Use the course gpu-cs2680 partition.
Assignment 5 HPC and/or API + AWS/CloudLab You serve the agent using the provided GPU, you will optimize your model and serving engine, but you can also use a small number of API calls.
Final project Laptop + model API, or HPC; CloudLab when necessary Use the API for hosted models and the HPC when you need to serve or train a model. Use CloudLab only when the research question depends on bare-metal control or isolation.

If a project needs hardware that none of these environments provides, ask the instructor while the scope can still change. Compute can sometimes be arranged; last-minute capacity cannot be promised.


Tips

  • Keep secrets out of agent sessions. A transcript can contain files the agent read and output its commands printed, not just your prompts. Follow the scan-before-you-archive checklist every time.
  • Describe your environment and experiment setup. Report the GPU, driver, serving engine and version, model, and workload. Latency or throughput without that context cannot be reproduced or compared.
  • Release idle resources. Exit the Slurm job, stop the EC2 instance, and terminate the CloudLab experiment. Shared hardware and paid instances should never sit idle by accident.
  • Escalate access problems early. An account problem in week one is fixable. The same problem on the due date is still an account problem, not an extension plan.