Nebius
Senior Technical Program Manager – LLM Inference
$147K–$224K
Palo Alto, California, United States · Manager · Full-time · Posted Aug 10, 2026
- Visa sponsorship
- Applicants must be authorized to work in the country in which they apply and provide proof of employment eligibility as a condition of hire.
About the job
Coordinate cross-functional delivery of AI models and GPU platforms from validation and infrastructure readiness through production serving and customer availability.
What you'll do
- Lead model and template delivery from model weights through validation to production endpoints, coordinating onboarding and customer availability.
- Coordinate new GPU platform bring-up for serving, including engine and kernel readiness, benchmarking, and template migration.
- Build execution plans, manage dependencies and risks, facilitate technical decisions, and improve delivery processes across engineering teams.
What they ask for
- Excellent project management and delivery skills, including breaking ambiguous initiatives into executable plans.
- Ability to identify critical paths and coordinate complex dependencies and parallel workstreams.
- Strong risk management, prioritization, and communication skills in English.
- Strong technical background to understand engineering discussions, infrastructure dependencies, and architectural trade-offs.
Nice to have
- Experience with GPU infrastructure, AI/ML platforms, or large-scale inference systems.
- Experience delivering cloud infrastructure or data center deployment projects; familiarity with capacity planning, production operations, and reliability engineering.
Pay
$147,200 — $224,000 USD base salary
Tools
GPU
AI focus
Coordinate delivery of AI models and LLM inference platforms, including model validation, production serving, and GPU platform readiness.
Model-written summary · the original posting is authoritative