Group Product Manager — Inference & Token Infrastructure

Volta; Palo Alto, Northern (CA, KY); Hybrid; USD 180,000 - 230,000; Full time

Benefits offered by this job

Competitive salary

Equity in Volta

Retirement/pension contributions

Comprehensive health benefits

Generous vacation days

Job summary

Volta seeks a Group Product Manager for inference infrastructure and the token factory in Palo Alto. You will lead a team of product managers focused on making AI workloads faster, cheaper, and more reliable, turning compute into tokens at scale.

You will partner with platform engineering to define features, track performance metrics, and align roadmaps with customer needs in a fast-moving AI space.

Qualifications

• Significant product management experience in AI/ML infrastructure or inference serving is essential.
• Experience managing other product managers or leading a product team.
• Strong technical understanding of model serving, inference optimization, or GPU compute.
• A track record shipping infrastructure products in a fast-evolving technical space.

Responsibilities

• Own product strategy and roadmap for inference infrastructure and token-serving capabilities.
• Lead and develop a team of product managers focused on inference and serving infrastructure.
• Partner with platform engineering to define features that improve inference throughput, latency, and cost efficiency.
• Track industry and customer trends in inference workloads and translate them into roadmap priorities.
• Define and monitor metrics for inference performance and efficiency.
• Represent inference and token-serving priorities in cross-functional and leadership planning.
• Work with key customers to understand evolving inference needs.

Skills

Product management

Team leadership

Technical understanding

Job description

Volta seeks a Group Product Manager for inference infrastructure and the token factory in Palo Alto. You will lead a team of product managers focused on making AI workloads faster, cheaper, and more reliable, turning compute into tokens at scale.

You will partner with platform engineering to define features, track performance metrics, and align roadmaps with customer needs in a fast-moving AI space.