How NVIDIA engineers and researchers build with Codex

At NVIDIA, engineers are using Codex as their default tool for complex engineering work, and to run end-to-end machine learning experiments. Codex, built on GPT‑5.5 and running in production on NVIDIA GB200 and GB300 infrastructure, can handle much longer, more autonomous sessions — going beyond execution to surface issues and ideas that weren't part of the original prompt.

“Codex is our go-to tool for complex engineering tasks, and with GPT-5.5, it surfaces bugs and gaps in my program that other models weren’t able to find.”

—Dennis Hannusch, Senior Software Engineer

Building and shipping production systems

NVIDIA’s coding agents team helps engineers across the company adopt and use AI tools effectively in real-world development workflows. Codex with GPT‑5.5 has become their go-to tool for complex engineering tasks.

“I’ve personally found Codex with GPT‑5.5 to be way more autonomous, with much less handholding,” explains Dennis Hannusch, a senior software engineer on the agents team. “I’m able to go for long sessions with multiple compactions and find that it still performs with top accuracy and manages to keep the work in context. And it’s great at tactically selecting the right tools as well as the right skills.”

Hannusch has already used Codex to evolve an internal platform from an MVP into a production-ready system, improving scalability and reliability along the way, something that had proven difficult with earlier models.

The team has also built an internal podcast recording app, similar to Riverside, spun up in just hours using Codex. “Given our privacy constraints, it would have taken us weeks to procure software,” Hannusch explains.

Using the Codex desktop app with computer interaction, the system was also able to test the video and audio recording functionality as it was built. “I didn’t have to do anything—it was built and tested completely autonomously,” he says. “Codex has completely changed the threshold for what’s worth building.”