Senior AI Platform Engineer & Architect (Real-time Inference)

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

Job summary

Ethereum Technologies in Concord, CA, is seeking an AI Platform Engineer & Architect for a 12-month W-2 contract. You will design and implement model-serving architectures for real-time inference, standardize deployment patterns on Kubernetes, and lead API-based inference services.

The role requires expertise in Kubernetes, CI/CD, and IaC, with proficiency in Python/Java/Go, and collaboration with Data Science, MLOps and Infra teams to ensure reliable production operations.

Qualifications

• Experience with real-time inference architectures.
• Proficiency in Kubernetes-based platforms and CI/CD.
• Strong programming skills in Python, Java or Go.

Responsibilities

• Design highly available, low-latency model-serving architectures for real-time inference.
• Develop deployment patterns for scalable AI/ML services on Kubernetes.
• Lead API-based inference service design, integration and lifecycle management.
• Optimize model-serving performance with latency tuning and autoscaling.
• Establish monitoring, SLOs/SLAs, alerting and runbooks for production services.
• Collaborate with Data Science, MLOps and Infra teams to ensure reliable production operations.

Skills

Online inference

Distributed systems

Kubernetes

CI/CD

IaC

Python

Java

Go

Monitoring

Cloud & on-prem

Tools

Kubernetes

Service mesh

CI/CD pipelines

IaC tooling

Job description

Ethereum Technologies in Concord, CA, is seeking an AI Platform Engineer & Architect for a 12-month W-2 contract. You will design and implement model-serving architectures for real-time inference, standardize deployment patterns on Kubernetes, and lead API-based inference services.

The role requires expertise in Kubernetes, CI/CD, and IaC, with proficiency in Python/Java/Go, and collaboration with Data Science, MLOps and Infra teams to ensure reliable production operations.