LLM Ops Engineer: Build & Scale a Secure AI Platform

FREEDOM SOLUTIONS GR; Denver (CO); Hybrid; USD 105,000 - 130,000; Full time

Job summary

Litera in Denver, CO is seeking an experienced LLM Ops Engineer to build and operate a secure AI platform that enables engineering teams to deploy models across providers. The role emphasizes reliability, governance, and cost-aware operations in production environments.

You’ll collaborate with global teams to scale AI capabilities, implement testing frameworks, and deliver observability through dashboards and SLIs. A hybrid work setup with in-office days is expected.

Qualifications

• 3+ years in DevOps, Platform Engineering or MLOps with hands-on LLM production experience.
• Experience deploying and scaling models across AI providers (OpenAI, Azure OpenAI, AWS Bedrock, Google Vertex).
• Strong Python skills and ability to build scalable, secure infrastructure.

Responsibilities

• Build and operate a scalable AI platform enabling model deployment across providers and environments.
• Ensure high availability and resiliency of AI services with production-grade infrastructure.
• Establish secure AI operations guarding access, data protection, and governance.
• Create unified developer experiences with APIs, tooling, and self-service capabilities.
• Optimize performance, reliability, and cost efficiency with monitoring and strategy management.
• Lead evolution of Litera’s AI operations capabilities by evaluating new tech and scalable solutions.
• Deliver observability with dashboards, alerts, and service-level metrics.
• Support safe deployment of AI solutions with testing frameworks and production readiness standards.

Skills

DevOps

Platform Engineering

MLOps

Python

API management

Gateways

Production-grade AI service operations

Load balancing

Secrets management

Access controls

Tools

Kubeflow

MLflow

Apache Airflow

Job description

Litera in Denver, CO is seeking an experienced LLM Ops Engineer to build and operate a secure AI platform that enables engineering teams to deploy models across providers. The role emphasizes reliability, governance, and cost-aware operations in production environments.

You’ll collaborate with global teams to scale AI capabilities, implement testing frameworks, and deliver observability through dashboards and SLIs. A hybrid work setup with in-office days is expected.