remote
AI Architect - VDart Inc
Software Engineer
Lead the design of a scalable enterprise AI platform, orchestrating LLM APIs, GPU compute pools, sandbox provisioning, and secure model registry. Define standards, guardrails, and reference architectures to enable consistent AI delivery across teams.
About the role
Key Responsibilities
- Design and evolve the enterprise AI platform architecture, covering LLM API gateway, GPU and compute allocation pools, sandbox provisioning, model registry, and security gate automation.
- Define infrastructure standards, API gateway patterns, and reference architectures for all AI delivery towers and partner integrations.
- Establish guardrails for token metering, rate limiting, audit logging, and compliance across the platform.
- Collaborate with data, security, and operations teams to ensure seamless integration and governance of AI services.
- Drive continuous improvement of platform performance, scalability, and cost efficiency.
Requirements
- Proven experience designing large‑scale AI or ML platform architectures, including LLM deployment and GPU compute management.
- Strong knowledge of API gateway design, rate limiting, token metering, and audit logging best practices.
- Hands‑on experience with cloud infrastructure (AWS, Azure, or GCP) and container orchestration (Kubernetes).
- Familiarity with security and compliance frameworks for AI services.
- Excellent communication skills and ability to translate technical concepts to cross‑functional stakeholders.