Senior Infrastructure Engineer at VLM Run

As a Senior Infrastructure Engineer at VLM Run, you will architect the core cloud infrastructure powering high-throughput VLM inference. You’ll own Kubernetes orchestration, GPU-accelerated workloads, and security compliance for enterprise customers. This is a high-impact, hands-on role in a sub-10 person team building the reliable backbone for next-generation visual AI.

• Design and manage production Kubernetes clusters and Terraform-based IaC to support high-performance API serving and mission-critical enterprise workloads.
• Optimize GPU orchestration and inference scaling to ensure low-latency performance and high reliability for complex, production-grade Vision-Language Models.
• Implement and maintain SOC 2 Type II and HIPAA-compliant security protocols, enabling secure deployments within customer VPCs across diverse enterprise industries.

• Possesses deep experience with cloud infrastructure, including Kubernetes, Infrastructure as Code, and building production systems from zero in a startup environment.
• Demonstrates proficiency in Python or Go, with a strong background in backend systems and ideally some exposure to ML model serving or inference infrastructure.
• Thrives in a hands-on, high-ownership role and is committed to an in-person culture in Santa Clara to drive rapid technical iteration with the founding team.

• Join a small, elite team of fewer than 10 people led by an MIT PhD founder with deep expertise in robotics and ML from Toyota Research Institute.
• Build the infrastructure layer for the rapidly evolving Vision-Language Model market, solving complex GPU orchestration and low-latency inference challenges for enterprise-scale workloads.
• Enjoy significant ownership and equity in a well-funded startup tackling the massive opportunity of structured data extraction from visual media for finance and physical AI.