AI Inference Engineer
- Remote, United States
- Senior
- Posted 6 days ago
or apply from Claude / ChatGPT / Muse
Founding engineer to own the inference serving layer for high-performance compute, reporting to the CTO at an energy startup.
About the role
Data centres are becoming a major electricity demand, and the company is building GPU and inference serving from scratch. This role owns how models are served, scaled, and delivered against performance targets.
At a glance
- Pay
- Not stated in the posting
- Remote scope
- Remote, United States
- Seniority
- Senior
- Skills
- CUDA, vLLM, TensorRT-LLM, SGLang, Triton Inference Server
- Posted
- 10 Nov 2026
- Last checked
- 16 Nov 2026
What you will do
- Define the inference serving strategy and architecture from first principles
- Build request routing, batching, scheduling, and autoscaling for latency-sensitive workloads
- Decide on model-level optimisation like quantisation, distillation, and speculative decoding
- Make architecture calls on serving frameworks such as vLLM, TensorRT-LLM, SGLang, or Triton
- Work with CUDA and GPU engineers to integrate custom kernels into the serving layer
What they look for
- Hands-on experience with batching, KV-cache management, quantisation, and speculative decoding
- Strong systems thinking across the full request path in a large cluster
- Comfort working directly with GPU/CUDA engineers on low-level performance work
- Track record of high-stakes architecture decisions and owning outcomes
Nice to have
- Experience with Triton or custom ML inference/training frameworks
How Keywordise applies for you
Alex Demo
[email protected]
From your CV
Yes, fully remote
- Sent
- 09:41
- Attached
- Your tailored CV
- 1Upload your CVAdd your CV once. It takes about a minute.
- 2Tailored to this jobKeywordise writes a CV and a cover letter for this job from your real experience.
- 3The form fills itselfName, email, experience and screening questions, field by field.
- 4Application sentYou get a receipt and follow it in your dashboard.
Apply with Keywordise AI7-day free trial, no card.
Apply from your AI assistant
Connect Keywordise to your assistant once, then send it the prompt. It applies for you.
Claude
- In Claude, open Settings, then Connectors, and choose Add custom connector.
- Name it Keywordise and paste the connector URL.
- Click Connect, log in to Keywordise and approve. Then send the prompt in a new chat.
https://keywordise.com/mcpDisconnect any time in your Keywordise settings.
ChatGPT
- In ChatGPT, open Settings, then Connectors. On plans that need it, turn on developer mode first.
- Add a new connector with the connector URL and choose OAuth. Leave the client ID and secret empty.
- Log in to Keywordise and approve. Then send the prompt in a new chat.
https://keywordise.com/mcpDisconnect any time in your Keywordise settings.
Muse
- Open Muse (muse.ai or the app) and send it the message below.
- If Muse asks how to sign in, answer OAuth. Open the sign-in link it sends, log in to Keywordise and approve.
- Send the prompt. Muse asks before it sends anything.
Add a custom connector called Keywordise. It is a remote MCP server at https://keywordise.com/mcp and uses OAuth. Give me the sign-in link.Muse is available in the US only for now.
Apply to Keywordise job utortxschkQuestions about this job
Is this a remote job, and where can I work from?
Yes. The posting lists AI Inference Engineer as a remote role for candidates in the United States.
What does this job pay?
No pay range is stated in the posting.
What experience is needed?
It is a senior role. The posting asks for: hands-on experience with batching, KV-cache management, quantisation, and speculative decoding; strong systems thinking across the full request path in a large cluster; comfort working directly with GPU/CUDA engineers on low-level performance work. Skills it names include CUDA, vLLM, TensorRT-LLM, SGLang.
How do I apply with Keywordise AI?
Select Apply with Keywordise AI, sign up and upload your CV. Keywordise writes a CV and a cover letter for this job from your real experience and applies for you. The 7-day free trial needs no card.
More remote IT and software jobs
- FEFuse EnergyAI Inference Engineer
- Remote, United Kingdom
- DdeCircleAI Field Engineer, Enterprise
- USD 176,000 to 224,000 per year
- Remote, worldwide
- NNVIDIASenior Solutions Architect, Gen AI
- USD 184,000 to 287,500 per year
- Remote, United States
CVEDIAAgentic AI Engineer, Computer Vision- Remote, Spain
- NNVIDIASenior Software Engineer, Aerial Platform
- Remote, United States
- NNVIDIASenior Software Engineer, AI Frameworks
- Remote, United States