Staff Technical Program Manager
You will connect model engineering, IaaS, product, and data center operations to deliver a reliable inference platform. You will own multi-quarter program delivery, coordinate model onboarding and optimization, manage production readiness, build execution frameworks, identify risks, and align technical stakeholders.
Responsibilities
- Own multi-quarter release planning and dependency governance
- Deliver executive communications across the Managed Inference platform
- Drive model version rollouts and inference optimization campaigns
- Prepare SLA readiness for new GPU hardware
- Manage multi-tenant capacity planning
- Coordinate Model Engineering, IaaS, Cloud Foundations, Data Center Operations, and external model providers
- Identify risks across model serving, reliability, capacity, and vendor timelines
- Build TPM execution frameworks
- Maintain execution dashboards
- Deliver data-driven executive updates
- Plan model onboarding on new GPU generations
- Validate firmware, drivers, CUDA, and ROCm stacks
- Define inference commissioning criteria
- Drive alignment across technical stakeholders
Requirements
- 7+ years of Technical Program Manager experience
- LLM inference and model serving knowledge
- Familiarity with batching strategies and quantization approaches
- Understanding of latency, throughput, and cost trade-offs
- Multi-tenant systems experience
- Familiarity with isolation, quota management, and SLA enforcement
- Familiarity with fine-tuning and alignment workflows
- Ability to build execution models in low-structure environments
- Exceptional written and verbal communication
- Daily use of AI tools for program execution
- Ability to influence engineering, product, and infrastructure leadership without direct authority
Benefits
- Pension contributions
- Additional perks supporting work-life balance