Principal Engineer, Model Optimizations
- Seattle, WA
- Lead
- Posted 5 weeks ago
or apply from Claude / ChatGPT / Muse
Own how models are optimized for serving across a mixed NVIDIA and AMD GPU fleet, from quantization to kernels, so every model runs well on every chip.
About the role
A principal engineer who likes thinking big and works well in a fast-moving industry. The gap between a model that runs and one that runs well costs millions in GPU time and decides whether customer SLOs are met.
At a glance
- Pay
- Not stated in the posting
- Location
- Seattle, WA
- Seniority
- Lead
- Skills
- CUDA, Triton, CUTLASS, ROCm, HIP, vLLM, SGLang, TensorRT-LLM
- Posted
- 8 Oct 2026
- Last checked
- 16 Nov 2026
What you will do
- Set technical strategy for model optimization across the fleet, choosing which techniques to invest in or take upstream
- Own quantization end to end, including calibration, accuracy budget and eval gates
- Drive execution-level performance for MoE routing, attention variants and long-context memory patterns
- Lead speculative decoding work and acceptance-rate tuning
- Write and tune kernels in CUDA, Triton and CUTLASS, plus ROCm counterparts, and know when not to
- Define parallelism layouts per model, GPU family and traffic shape, and make them repeatable
What they look for
- 12 or more years in performance-critical systems
- Deep experience with quantization schemes such as FP8, FP4/MXFP4, INT8, AWQ and GPTQ
- Familiarity with CUDA, Triton, CUTLASS and ROCm tooling like HIP and Composable Kernel
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 53l2n7aeyaQuestions about this job
Where is this job based?
The posting lists Principal Engineer, Model Optimizations as a role based in Seattle, WA, United States.
What does this job pay?
No pay range is stated in the posting.
What experience is needed?
It is a lead role. The posting asks for: 12 or more years in performance-critical systems; deep experience with quantization schemes such as FP8, FP4/MXFP4, INT8, AWQ and GPTQ; familiarity with CUDA, Triton, CUTLASS and ROCm tooling like HIP and Composable Kernel. Skills it names include CUDA, Triton, CUTLASS, ROCm.
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 engineering jobs in Seattle, WA
- SStripeEngineering Manager, Collaboration Engineering
- Seattle, WA
- SSoFiSenior Staff Incident Response Engineer
- Seattle, WA
- ZZZINC Zillow, Inc.AV Engineer
- USD 101,600 to 162,400 per year
- Seattle, WA
Blue Origin Personnel, LLCTestbed Development Engineer- Seattle, WA
- A space infrastructure manufacturerAvionics Integration & Test Engineer
- Seattle, WA
- A company building safe AI systemsPrincipal Engineer Capacity/Compute
- Seattle, WA