AI Platform Engineer — Self-Service, Guarded AI Systems

Quantum Technologies. LLC; Boston (MA); Sur place; USD 140 000 - 190 000; Plein temps

Résumé du poste

Quantum Technologies. LLC is seeking a platform engineer to stand up and scale AI compute environments, including GPU-backed resources and containerized workloads. The role focuses on automated rollouts, grounded retrieval systems, and secure access controls, with emphasis on guardrails and governance.

You will monitor health, usage, and costs while enabling self-service across teams. You will work across infrastructure, automation, integration, and application code, applying cost-aware

Qualifications

• 4+ years platform engineering, cloud infra or DevOps.
• Experience running AI/LLM platforms in production, including retrieval systems grounded in company data.
• AI systems require testing, evaluation, and monitoring to catch issues early.
• Strong Python skills and API integration experience.
• Cloud and container experience with AWS or Azure.
• Knowledge of cost versus performance tradeoffs in AI models.
• Experience exposing metrics via APIs or dashboards for visibility beyond the team.
• Security-focused development with least-privilege access and data handling best practices.
• Self-service mindset with governance to enforce guardrails.
• Comfort across infrastructure, automation, integration, and application code.

Responsabilités

• Stand up and maintain the compute environment for AI workloads, including containerized and GPU-backed resources.
• Automate safe rollouts with rollback built in to update AI platforms.
• Build retrieval systems to ground model responses in real company data.
• Maintain vector stores and data sources relied on by retrieval.
• Route and gate model access to appropriate models and providers.
• Redact sensitive data from prompts before model execution.
• Implement guardrails to catch harmful or incorrect AI output.
• Enable self-service access with governance and permissions.
• Monitor system health, latency, and error rates; preempt problems.
• Track usage and spend at model and feature levels to avoid cost surprises.
• Apply cost discipline across AI spend.
• Develop self-service tools and APIs for other teams to ship AI features.
• Report AI performance metrics via dashboards and APIs.

Connaissances

Platform engineering

AI in production

AI systems judgment

Python programming

Cloud & containers

Cost and model judgment

APIs & dashboards

Security mindset

Self-service thinking

Full-stack

Outils

Terraform

FinOps

Retrieval pipelines

Vector databases

Container orchestration

Description du poste

Quantum Technologies. LLC is seeking a platform engineer to stand up and scale AI compute environments, including GPU-backed resources and containerized workloads. The role focuses on automated rollouts, grounded retrieval systems, and secure access controls, with emphasis on guardrails and governance.

You will monitor health, usage, and costs while enabling self-service across teams. You will work across infrastructure, automation, integration, and application code, applying cost-aware