Member of Technical Staff, Infrastructure ($120K – $250K + Equity) at The Token Company

The Token Company is a $12M seed-stage startup backed by First Round Capital, NEA, and YC, building specialized machine learning models to compress LLM inputs. By identifying and removing unimportant data before it hits expensive models, they drastically reduce inference costs for high-scale enterprises and tech companies integrating LLMs into their production workflows.

About the role

You will own the end-to-end cloud infrastructure for a high-performance compression API. This role involves building global, low-latency GPU ML inference systems that sit directly in the critical path of customer traffic. As a core member of a 5-person team, you will drive reliability, scalability, and cost-efficiency for a revolutionary AI product.

Responsibilities

• Architect and manage global, high-throughput GPU inference infrastructure using AWS, Terraform, and Docker to ensure maximum performance and uptime.
• Own the entire infrastructure stack from initial deployment and CI/CD pipelines to long-term reliability and cost-efficiency research.
• Collaborate closely with research and product teams to integrate and scale compression models into a high-traffic production API.

Requirements

• Demonstrated experience building and operating production-grade cloud infrastructure at scale using tools like AWS and Terraform.
• Strong background in managing containerized environments with Docker and establishing robust CI/CD pipelines for high-reliability systems.
• Proven ability to take end-to-end ownership of an infrastructure stack, ideally within a fast-paced startup or high-growth engineering environment.

Qualifications

• Bachelor’s degree in Computer Science, Electrical Engineering, or a related field.
• Experience with Kubernetes, Helm, and other container orchestration tools.
• Knowledge of cloud platforms such as AWS, Azure, or Google Cloud.
• Experience with Terraform and Docker.
• Strong problem-solving skills and the ability to work independently and collaboratively.

Skills

• Cloud infrastructure design and management.
• Containerization and orchestration.
• CI/CD pipeline development.
• Performance optimization.
• Scalability and reliability.

Benefits

• Unparalleled San Francisco living experience with provided housing, food, laundry, and cleaning services.
• Full visa sponsorship.

Pay

$120K – $250K + Equity

Schedule

Full-time

Location

San Francisco, USA