Apt Insight
Is This a Good Match for You?
Your match shows how your personality fits this role. It compares your working style and your priorities with how this employer works.It also weighs the things a job description cannot tell you, such as the culture, the management style and the stability of the company, against what matters most to you.
Unlock your full match with Apt ProStart with the AI-powered career test to unlock your personal career mentor, full company insights, and a personalized job board designed around your goals.
Responsibilities
Set the long-term strategy and roadmap for the open-weight LLM inference platform with cross-functional stakeholders.
Translate business goals into prioritized technical programs addressing cost per token, latency, throughput, reliability, and model coverage.
Lead GPU capacity planning, inference optimization, model migrations, and high-availability programs.
Build standardized frameworks to benchmark and evaluate models for serving performance, quality, and cost.
Provide data-backed recommendations to leaders and teams on model selection.
Partner with Security, Legal, and Compliance to establish policies and requirements for safe model adoption.
Manage programs end to end, including dependencies, forecasting, budgeting, scheduling, and delivery.
Qualifications
Have 10 or more years of experience on software teams as a Development Manager or Technical Program Manager, including at least 3 years on ML, AI platform, or large-scale infrastructure programs.
Have working knowledge of LLM architecture, inference optimization, serving frameworks, and GPU infrastructure economics.
Have experience with multi-vendor GPU or inference-provider strategies, AI cost management, and benchmarking and model evaluation methods.
Have a track record of delivering complex, cross-organizational technical programs with significant budgets.
Be able to turn business objectives into technical programs with measurable results and influence senior engineers and executives without direct authority.
Understand system flows, block architectures, and APIs; the role does not require writing or reading code.
Experience coordinating with cloud and GPU providers would be useful for managing external dependencies.
Strength in structured execution and sound technical judgment in ambiguous, evolving platform environments would support success.
Work Environment
The role is remote-eligible within the United States.
The listing identifies Mountain View, California, and Seattle, Washington, as locations.
You will collaborate across Engineering, Product, Security, Finance, Legal, and Compliance, as well as with external partners.
The listing does not specify working hours or travel expectations.
Benefits & Perks
The listed U.S. annual base pay ranges from $169,569 to $266,725, depending on geographic pay zone; the role may also be eligible for benefits, bonuses, commissions, and equity.
Listed benefits include health and wellbeing resources and paid volunteer days.
You can develop expertise in LLM infrastructure strategy, inference economics, model evaluation, and cross-organizational program leadership.