Inference Engineer

THE OPPORTUNITY

A role worth
a closer look.

Build the serving layer that turns models running on specialized accelerators into reliable customer services. Own request routing, batching, cache management and autoscaling, including production monitoring and incident response. As an early engineer, help decide the architecture and roadmap for an inference platform designed around alternative hardware.

Experience highlighted by the employer

• At least five years operating infrastructure systems, including real production experience serving language models.
• Strong concurrency, networking and scheduling fundamentals, plus experience owning reliability and on-call response.

Location & eligibility

Employer lists hybrid work in San Francisco or New York City. Confirm office attendance and US authorization or sponsorship directly; the reviewed description gives no sponsorship guarantee.

Compensation

See the employer’s original listing for current compensation details. We do not estimate an undisclosed currency or salary.

Before you apply

This is TaskBull’s concise summary, not the employer’s full job description. Review the complete responsibilities, terms, accessibility information and privacy notice on the original application page.