AI Platform Architect & Real-Time Inference Leader

Valiant Technologies LLC; Concord (CA); On-site; USD 83,000 - 113,000; Full time

Job summary

Valiant Technologies LLC seeks an AI Platform Engineer & Architect to design scalable model-serving systems in Concord, CA. The role focuses on building low-latency real-time inference, deploying AI/ML services across Kubernetes, and owning API-based inference lifecycle from design to production.

You will optimize performance, implement autoscaling, monitoring, and resiliency, and drive CI/CD integrations. Collaboration with Data Science, MLOps, and Infra teams is essential for enterprise-grade

Qualifications

• Experience with online inference serving architectures.
• Real-time APIs and distributed systems design experience.
• Kubernetes-based platforms, container orchestration, service mesh exposure.
• Knowledge of autoscaling, capacity management, and workload optimization.
• Experience with performance engineering, load testing, and latency optimization.
• Strong monitoring, observability, logging, tracing, and SLO management.
• Experience with CI/CD, DevOps, and Infrastructure as Code (IaC).
• Knowledge of reliability engineering, fault tolerance, and resiliency patterns.

Responsibilities

• Design and implement highly available, low-latency model-serving architectures for real-time inference workloads.
• Develop and standardize deployment patterns for scalable AI/ML services across Kubernetes platforms.
• Lead API-based inference service design, integration, deployment, and lifecycle management.
• Optimize model-serving performance through latency tuning, caching strategies, autoscaling, and resource management.
• Establish monitoring, observability, SLOs/SLAs, alerting, and runbooks for production services.
• Drive load testing, capacity planning, resiliency engineering, and disaster recovery readiness.
• Integrate inference platforms with CI/CD pipelines for automated deployments and controlled releases.
• Collaborate with Data Science, Platform Engineering, MLOps, and Infrastructure teams to ensure reliable production model operations.
• Establish operational best practices, security standards, reliability measures, and performance benchmarks.

Skills

Online inference

Real-time APIs

Distributed systems

Kubernetes

Autoscaling

Performance engineering

Monitoring & observability

CI/CD & IaC

Cloud & on-prem

Backend programming (Python/Java/Go)

Tools

Kubernetes

Container orchestration

Service mesh

CI/CD tooling

IaC (Terraform/CloudFormation)

Job description

Valiant Technologies LLC seeks an AI Platform Engineer & Architect to design scalable model-serving systems in Concord, CA. The role focuses on building low-latency real-time inference, deploying AI/ML services across Kubernetes, and owning API-based inference lifecycle from design to production.

You will optimize performance, implement autoscaling, monitoring, and resiliency, and drive CI/CD integrations. Collaboration with Data Science, MLOps, and Infra teams is essential for enterprise-grade