MLOps Engineer

AKIVA AI, LLC; Northern (KY); Hybrid; USD 120,000 - 180,000; Full time

Benefits offered by this job

401(k) match

Medical Insurance

Vision Insurance

Disability Insurance

PTO

Profit Sharing

Job summary

AKIVA AI, LLC is seeking an experienced MLOps/Platform Engineer to build and maintain the infrastructure that trains, deploys, and monitors ML models in production.

Responsibilities include owning CI/CD, observability, and reliability across the AKIVA AI platform, with emphasis on GPU scheduling, multi-region deployment, and cost optimization.

Qualifications

• 3+ years of experience in MLOps, platform engineering, or SRE for ML systems.
• Hands-on with Kubeflow, SageMaker, Vertex AI, or MLflow.
• Solid understanding of model serving patterns and GPU scheduling.

Responsibilities

• Build CI/CD for model training, evaluation, and deployment.
• Operate model serving infrastructure across cloud regions.
• Implement model monitoring, drift detection, and automated rollback.
• Manage GPU infrastructure, autoscaling, and cost optimization.
• Partner with security and compliance for enterprise requirements.

Skills

MLOps

Platform engineering

SRE for ML

Tools

Kubeflow

SageMaker

Vertex AI

MLflow

Job description

AKIVA is an AI-native engineering firm specializing in enterprise services, domain-specific solutions, and high-performance infrastructure from strategy through deployment. We build innovative systems that drive measurable results for commercial enterprises and government agencies. AKIVA is a certified Service-Disabled Veteran-Owned Small Business (SDVOSB).

Position Overview

Build and maintain the infrastructure that trains, deploys, and monitors machine learning models in production. Own the CI/CD, observability, and reliability layers of the AKIVA AI platform.

Key Responsibilities

• Build CI/CD for model training, evaluation, and deployment
• Operate model serving infrastructure across multiple cloud regions
• Implement model monitoring, drift detection, and automated rollback
• Manage GPU infrastructure, autoscaling, and cost optimization
• Partner with security and compliance to meet enterprise and federal requirements

Required Qualifications

• 3+ years in MLOps, platform engineering, or SRE for ML systems
• Hands-on with at least one ML platform (Kubeflow, SageMaker, Vertex AI, MLflow)
• Solid understanding of model serving patterns and GPU scheduling

Preferred Qualifications

• Experience with vLLM, TensorRT-LLM, or Triton Inference Server in production
• Multi-cluster GPU operations
• FedRAMP, IL4/5, or other compliance program experience

Tools, Technologies & Frameworks

What AKIVA Offers

• Professional development and skill-building opportunities
• Supportive management team with Veteran-owned company values
• Opportunity to work on impactful client engagements
• Long-term contract engagement with potential for extension
• AI productivity tools and training provided at no cost to employees
• 401(k) with generous company match
• Medical Insurance
• Vision Insurance
• Short-Term & Long-Term Disability Insurance
• Paid Time Off (PTO)
• Profit Sharing

Equal Employment Opportunity Statement

AKIVA is committed to providing an environment of mutual respect where equal employment opportunities are available to all applicants and teammates without regard to race, color, religion, sex, national origin, age, physical disability, marital status, military and Veteran status, or any other characteristic protected by applicable law. We believe that diversity among our teammates is critical to our success as a company, and we seek to recruit, develop, and retain the most talented people within a qualified candidate pool.

AKIVA is a certified Service-Disabled Veteran-Owned Small Business (SDVOSB).