Sollert Engineering Cloud (Demo) is hiring
Principal AI Infrastructure Engineer
📍 San Francisco, CA / RemoteFull-Time•Posted September 28, 2026
About this Role
Build ultra-low-latency model serving clusters, continuous fine-tuning pipelines, and adaptive telemetry for foundation models.
Qualifications & Requirements
6+ years experience with distributed model serving (vLLM, TensorRT-LLM), CUDA kernel tuning, and GPU orchestration in Kubernetes.
Required Skills & Technologies
PythonLLM InferencevLLMTritonCUDAKubernetesPyTorch
Common Questions
Where is this role based?
This role is based in San Francisco, CA / Remote.
What type of employment is this?
This is a full-time position with Sollert Engineering Cloud (Demo).
How do I apply?
Click the “Apply for this Role” button on this page, upload your resume (PDF or Word), and fill in your contact details. Your application goes directly to the recruiting team at Sollert Engineering Cloud (Demo).
What happens after I apply?
Your resume is read and scored by AI instantly. The recruiting team reviews your profile, and if there’s a match you will hear from them directly. You can track your application status in the candidate portal at any time.
Ready to Join Sollert Engineering Cloud (Demo)?
Upload your resume and apply in under 2 minutes. Your skills are read by AI automatically — no long forms, no waiting.
Already applied? Track your application →