Senior Technical Program Manager – LLM Inference
Nebius, Palo Alto, California +1
What you will do
- Leading template and model delivery – from weights through validation to production endpoint.
- Coordinating model onboarding and production delivery, from infrastructure readiness to successful customer availability.
- Running the Applied AI / Customer Delivery sync — driving open issues to resolution and unblocking teams between meetings.
- Coordinating the bring-up of new GPU platforms for serving — engine and kernel readiness, benchmarking against current hardware, and template migration once validated.
- Partnering with Token Factory Product on the serverless launch path — ensuring validated templates hand off cleanly into catalogue, model card, and public availability.
- Building and maintaining execution plans, identifying risks early, and ensuring blockers are resolved before they impact delivery.
- Working closely with engineering managers, technical leads, product managers, SRE, infrastructure, networking, security, and other platform teams.