Real-Time AI Platform Architect (Contract)

Robotics Technologies LLC; Concord (CA); On-site; USD 81,000 - 115,000; Full time

Job summary

Robotics Technologies LLC in Concord, CA seeks an AI Platform Engineer & Architect to design and implement high-availability model-serving systems for real-time inference, across Kubernetes-based platforms. The role involves building scalable deployment patterns and leading API-based inference service design.

You will collaborate with Data Science, Platform Engineering, MLOps and Infrastructure teams to ensure reliable production operations, establish monitoring and SLOs, and integrate inference

Qualifications

• Strong experience with online inference and production model-serving architectures.
• Hands-on Kubernetes, container orchestration, and service mesh experience.
• Proficiency in Python, Java, or Go.
• Experience with CI/CD, IaC, and cloud/on-prem platforms.

Responsibilities

• Design and implement low-latency, high-availability model-serving architectures.
• Develop deployment patterns for scalable AI/ML services on Kubernetes.
• Lead API-based inference service design, deployment, and lifecycle management.
• Optimize performance via latency tuning, caching, autoscaling, and resource management.
• Establish monitoring, observability, SLOs/SLAs, alerts, and runbooks.
• Drive load testing, capacity planning, resiliency engineering, and disaster recovery readiness.
• Integrate inference platforms with CI/CD for automated releases.
• Collaborate with Data Science, Platform Eng, MLOps, and Infra teams.
• Define operational best practices, security standards, reliability measures.

Skills

Kubernetes

Real-time inference

Distributed systems

API design

CI/CD / IaC

Performance tuning

Monitoring / Observability

Cloud & on-prem

Python / Java / Go

Tools

Docker

Istio / service mesh

CI/CD pipelines

IaC (Terraform)

Job description

Robotics Technologies LLC in Concord, CA seeks an AI Platform Engineer & Architect to design and implement high-availability model-serving systems for real-time inference, across Kubernetes-based platforms. The role involves building scalable deployment patterns and leading API-based inference service design.

You will collaborate with Data Science, Platform Engineering, MLOps and Infrastructure teams to ensure reliable production operations, establish monitoring and SLOs, and integrate inference