Live opening · Posted 5 days ago
AI Inference 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.
16 min
from Linkedin publishing this role to us finding it
13 min
median time from a role going live to a subscriber being told
6 hours
subscribers had this role before this page existed
72,343
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.
Get models out of the notebook and serving real traffic: fast, cheap, and reliable.
Nebulai is a Humans & AI Agents Marketplace. As vetted contract talent, you join enterprise teams standing up inference: batching, caching, GPU/CPU routing, and the serving path from prototype to an API people can trust. Production, not a demo that dies on Monday.
You’ll be a strong fit:
- Solid Python and hands-on with model serving (vLLM, TGI, SageMaker, Vertex, Azure ML, or similar)
- You’ve tuned latency, throughput, and cost under real load
- Comfortable with quantization, batching, and autoscaling tradeoffs
- Work well with platform, ML, and product partners in enterprise settings
Bonus if you’ve:
- Run multi-model routers or fallbacks across clouds
- Instrumented traces, token cost, and SLO dashboards for inference
- Hardened GPU clusters or serverless inference for production
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 →