Remote AI Infrastructure Engineer — Scale ML & Inference

Vantaca, LLC; Redwood City, Northern (CA, KY); Hybrid; USD 150,000 - 190,000; Full time

Benefits offered by this job

Medical, Dental, Vision

Job summary

HOAi, now part of Vantaca, is seeking an AI Infrastructure Engineer to scale and maintain the infrastructure powering our AI-driven products. You will work at the intersection of infrastructure, MLOps, and product development, ensuring reliability, performance, and cost efficiency across AI services.

Ideal candidates bring 8+ years in infrastructure, strong cloud expertise, and experience with model serving, GPU optimization, and real-time inference.

Qualifications

• 8+ years in infrastructure engineering, DevOps, or SRE.
• Strong cloud platform expertise.
• Experience building and maintaining deployment pipelines.
• Experience with PostgreSQL, Redis, or other production databases.
• Experience with APM tools, metrics, logging, and alerting.
• Familiarity with vector databases and model serving frameworks.
• Managing and optimizing GPU work.
• Real-time inference with low-latency serving infrastructure.
• LLM deployment and performance improvements.

Responsibilities

• Profile and optimize AI workloads and pipelines for latency and cost.
• Build and maintain scalable, reliable cloud infrastructure.
• Develop CI/CD pipelines for models from development to production.
• Monitor and improve GPU utilization and memory usage.
• Design auto-scaling and disaster-recovery strategies.
• Ensure security and compliance across AI infrastructure.
• Collaborate with product and engineering for rapid feature deployment.

Skills

Cloud platforms

DevOps/SRE

GPU optimization

LLM deployment

PostgreSQL/Redis

Observability

Auto-scaling

Model serving frameworks

Vector databases

Security/compliance

Tools

CI/CD pipelines

Model deployment

Vector databases

APM tools

Job description

HOAi, now part of Vantaca, is seeking an AI Infrastructure Engineer to scale and maintain the infrastructure powering our AI-driven products. You will work at the intersection of infrastructure, MLOps, and product development, ensuring reliability, performance, and cost efficiency across AI services.

Ideal candidates bring 8+ years in infrastructure, strong cloud expertise, and experience with model serving, GPU optimization, and real-time inference.