C
Staff Technical Program Manager, Managed Inference
Sin especificarTiempo completoGestión de programasData InfrastructureCloud Computing
Lead end-to-end programs for a managed AI inference platform, coordinating model engineering, infrastructure, product, data center operations, and external model providers. Build execution frameworks and guide multi-quarter roadmaps, model onboarding, inference optimization, and production readiness
Responsabilidades
- Own multi-quarter release planning, dependency management, and executive communication for the managed inference platform.
- Lead model rollouts, inference optimization, GPU hardware SLA readiness, and multi-tenant capacity planning from kickoff through delivery.
- Coordinate programs across model engineering, infrastructure, cloud foundations, data center operations, and external model providers.
- Identify risks related to model serving, reliability, capacity, and vendor schedules before they affect delivery.
- Develop scalable program frameworks, execution dashboards, and data-driven leadership updates.
- Plan model onboarding on new GPU generations, including firmware and driver readiness, CUDA and ROCm validation, and workload commissioning criteria.
- Align engineering, product, and operations leaders, including highly technical stakeholders.
Requisitos
- At least 7 years of technical program management experience in fast-paced technical environments.
- Track record of owning complex programs across engineering and product organizations.
- Working knowledge of LLM inference and model serving, including batching, quantization, and latency, throughput, and cost tradeoffs.
- Familiarity with multi-tenant isolation, quota management, and SLA enforcement.
- Understanding of fine-tuning and alignment workflows sufficient to coordinate timelines and identify risks.
- Ability to establish execution processes where none exist and gain team adoption.
- Strong written and verbal communication for clear, data-driven executive updates.
- Daily use of AI tools to improve program execution, risk detection, and communication.
- Ability to align engineering, product, and infrastructure leaders without direct authority.
Se valora
- Experience with AI inference or training platforms.
- Experience leading model onboarding across GPU generations, including firmware, drivers, and stack validation.
- Experience mentoring junior technical program managers.
- Experience working with distributed teams.
- Background at a late-stage company or an AI infrastructure team at a hyperscaler.
Beneficios
- Benefits aligned with local market standards, including pension contributions and additional work-life balance perks.