Lead LLM/ML Ops

Oliver James Group; United States; Remote; USD 165,312,000 - 275,520,000; Full time

Job summary

Oliver James Group seeks a hands-on Lead AI Platform Engineer to build and operate production-grade AI infrastructure in AWS, focusing on LLMOps and MLOps. This is a remote, six-month contract with potential for full-time conversion.

You will design CI/CD pipelines, IaC, automation and monitoring; develop LLMOps capabilities including deployment, prompts, evaluation, observability and guardrails; manage model lifecycle, drift detection and retraining.

Qualifications

• Hands-on experience building production AI/ML infrastructure.
• Strong DevOps/SRE background.
• Experience with LLMOps/MLOps in production environments.
• Experience with CI/CD, IaC, automation, observability and production support.
• Understanding of enterprise AI security and governance.

Responsibilities

• Build and operate production AI/ML infrastructure in AWS.
• Design and maintain CI/CD pipelines, IaC, automation and monitoring.
• Develop LLMOps capabilities: deployment, prompt/version management, evaluation, observability and guardrails.
• Manage MLOps: model lifecycle, deployment, monitoring, drift detection and retraining.
• Establish repeatable deployment and promotion processes across dev/test/prod.
• Optimise AI workloads for latency, scalability, reliability, token consumption and cost.
• Implement security, access controls, data protection and governance.
• Build reusable platform capabilities for application teams to integrate AI without managing underlying infra.

Skills

LLMOps

MLOps

DevOps

SRE

AWS

CI/CD

IaC

Observability

Security governance

Tools

AWS

Terraform

Job description

Lead AI Platform Engineer - LLMOps / MLOps - Remote

6-month initial contract with potential for FTE conversion

We're looking for a hands-on AI Platform Engineer with strong LLMOps/MLOps and DevOps experience to help build and operate production-grade AI infrastructure within an AWS environment.

You'll work across engineering, data/AI, architecture and external development teams to create scalable, secure and repeatable AI platform capabilities.

What you'll be doing:

• Build and operate production AI/ML infrastructure, preferably within AWS
• Design and maintain CI/CD pipelines, infrastructure as code, automation and monitoring
• Develop LLMOps capabilities covering model deployment, prompt/version management, evaluation, observability and guardrails
• Manage MLOps processes including model lifecycle management, deployment, monitoring, drift detection and retraining
• Establish repeatable deployment and promotion processes across development, test and production
• Optimise AI workloads for latency, scalability, reliability, token consumption and cost
• Implement appropriate security, access controls, data protection and governance
• Build reusable platform capabilities that allow application teams to integrate AI without managing the underlying infrastructure
• Partner closely with application engineers, data/AI teams, architects and external development partners

What we're looking for:

• Strong hands-on experience building and operating production AI/ML infrastructure
• Solid DevOps/SRE background
• Experience with LLMOps and/or MLOps in production environments
• Strong AWS and cloud engineering experience
• Experience with CI/CD, IaC, automation, observability and production support
• Understanding of enterprise AI security and governance
• Ability to build scalable, reusable platform capabilities rather than one-off solutions
• Comfortable working across engineering, AI/data and architecture teams

No sponsorship available.