Member of Technical Staff, Infrastructure

The Token Company • San Francisco, CA

3d • Onsite

About The Position

The Token Company is a seed-stage startup focused on training machine learning models to compress raw LLM inputs, thereby reducing inference costs for LLMs. As a Member of Technical Staff on the infrastructure team, you will be responsible for the end-to-end cloud systems serving our compression API. This includes building and managing global, low-latency, high-throughput GPU ML inference infrastructure that handles critical customer traffic, focusing on deployment, scaling, reliability, and cost-efficiency. This role offers high ownership and requires continuous learning and research into new technologies.

Requirements

• Comfortable with AWS, Terraform, Docker and CI/CD.
• Experience building for performance and reliability at scale.
• Have owned an infra stack end-to-end.
• Experience building and operating production infrastructure yourself before, at a startup or a larger company.
• A quick learner, able to grasp the product and systems and move fast.

Responsibilities

• Own the cloud systems that serve our compression API end-to-end.
• Build global low-latency, high-throughput GPU ML inference infra.
• Manage deployment and scaling of infrastructure.
• Ensure reliability and cost-efficiency of the infrastructure.
• Continuously improve and research new solutions and technologies.

Benefits

• Significant equity
• Housing
• Food
• Laundry and cleaning in SF
• Visa sponsorship

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: No Education Listed