Live opening · Posted 5 days ago
AI Runtime Engineer
Nebulai · United States (Remote)
You are 5 days behind. JobBeeper subscribers saw this role while it was still new.
At a glance
The key details from the original listing.
CompanyNebulai
LocationUnited States (Remote)
Work modeYes
Source
Linkedin
Listed5 days ago
Your early-applicant advantage
Live timing from JobBeeper.
18 min
from Linkedin publishing this role to us finding it
14 min
median time from a role going live to a subscriber being told
6 hours
subscribers had this role before this page existed
72,926
roles found in the last 24 hours — the newest are not on this site yet
About the role
Description supplied by the original job listing.
Own the layer between a trained model and something that actually runs—kernels, executors, and the runtime choices that make latency and cost real.
Nebulai is a Humans & AI Agents Marketplace. As vetted contract talent, you join enterprise teams hardening AI runtimes: execution engines, graph compilers, memory layouts, and the path from a packed artifact to stable inference in production. Not a notebook wrapper. A runtime people can ship on.
You’ll be a strong fit:
- Solid Python plus C++ or systems comfort around runtimes
- Hands-on with ONNX Runtime, TensorRT, TorchScript/Inductor, TVM, XLA, or similar
- Care about memory, kernels, concurrency, and reproducible performance
- Comfortable pairing with ML, platform, and infra partners in enterprise settings
Bonus if you’ve:
- Built custom ops, plugins, or graph passes for a serving stack
- Tuned GPU/CPU runtimes for LLMs, vision, or multimodal models
- Shipped runtime upgrades without breaking production traffic
Contract work via Nebulai’s marketplace. Apply at https://nebulai.app
Work arrangement
Yes
More openings worth a look
Recently tracked roles with full details and direct application links.
Good roles move before most people even see them.
Tell JobBeeper what you want and get fresh matches delivered in minutes.
Start your free trial →