Real-Time AI Inference Engineering Lead

VDart Inc; Charlotte (NC); Hybrid; USD 140,000 - 190,000; Full time

Job summary

VDart Inc. is seeking an Inference Lead in Charlotte, NC. The role focuses on designing and industrializing low-latency model-serving services for predictive AI, with hybrid work options and cross-cloud/on-prem deployment considerations.

The candidate will define deployment patterns, capacity controls, monitoring standards, and operational practices to ensure reliable, scalable inference across environments. Experience leading inference and platform teams is preferred.

Qualifications

• Experience with real-time model serving
• Proficient in designing scalable inference platforms
• Familiarity with cloud and on-prem deployments

Responsibilities

• Architect low-latency online inference and real-time model-serving solutions.
• Develop scalable APIs, microservices, and deployment patterns for predictive models.
• Implement Kubernetes-based deployment, autoscaling, load balancing, and traffic-management strategies.
• Conduct benchmarking, performance tuning, capacity planning, and load testing.
• Design monitoring, SLOs, runbooks, and incident-response practices.

Skills

Online inference architecture

REST/gRPC APIs

Kubernetes

Performance optimization

Monitoring & SLOs

CI/CD pipelines

Resilience & HA

Cloud & on-prem deployment

Education

Degree in CS/Engineering

Job description

VDart Inc. is seeking an Inference Lead in Charlotte, NC. The role focuses on designing and industrializing low-latency model-serving services for predictive AI, with hybrid work options and cross-cloud/on-prem deployment considerations.

The candidate will define deployment patterns, capacity controls, monitoring standards, and operational practices to ensure reliable, scalable inference across environments. Experience leading inference and platform teams is preferred.