AI Platform Ops Engineer

Job title: AI Platform Ops Engineer

Location:Englewood, CO

Duration: 2+ Months

Description:
The Agentic AI Engineer role exists to scale and secure the enterprise Databricks platform on AWS that supports EchoStar's production analytics, machine learning, and AI agent workloads. This role solves problems in platform reliability, data governance under Unity Catalog, CI/CD automation, and the integration layer for AI agent frameworks including MCP servers. The team is building the foundational platform layer that EchoStar's GenAI products run on, so decisions made in this role carry direct impact on AI product velocity, security posture, and governance compliance across the enterprise. This is a hands-on engineering position that requires production Databricks experience, infrastructure automation skills, and genuine interest in AI platform governance.

Objectives

* Provision, manage, and continuously improve Databricks workspaces at production scale using Terraform and automated deployment patterns, and take ownership of platform monitoring and incident response.
* Standardize Unity Catalog adoption across the platform, applying data sensitivity classifications including PII, CPNI, and PCI so access control stays consistent and auditable.
* Support the integration of AI agents into the platform by implementing and maintaining Model Context Protocol (MCP) server frameworks and managing authentication for agentic access patterns.
* Build and maintain CI/CD pipelines for Databricks Asset Bundle deployments, and reduce manual toil through self-service tooling on the team's internal developer portal.
* Enforce cluster policies and contribute to cost attribution efforts that connect platform spend to the workloads and teams responsible for it.
* Provide technical guidance to junior team members and document platform patterns that strengthen the team's shared knowledge base.

Core Skills and Competencies (What You'll Bring)

* Critical experience administering Databricks in a production environment, including workspace management, cluster configuration, Unity Catalog governance, and job orchestration.
* Strong Python and Bash scripting ability applied to real automation problems, along with working knowledge of Terraform and CI/CD pipeline design.
* Working knowledge of AWS services relevant to a cloud-native data platform, including IAM, S3, and VPC, gained through experience operating infrastructure in a regulated enterprise environment.
* AI literacy spanning how ML models are served, what agent frameworks require from infrastructure, and how access patterns for AI workloads differ from batch analytics.
* Practical understanding of metadata management, data classification, and access control in a Lakehouse or Lakehouse-adjacent architecture.
* Strong collaboration and communication skills, including the ability to explain technical decisions clearly and push back constructively when a proposed approach introduces platform risk.

Additional Qualifications

Successful candidates will typically have:
* Experience with Databricks Asset Bundles and CI/CD patterns for Databricks deployments.
* Familiarity with Unity Catalog administration and data classification frameworks.
* Exposure to AI agent frameworks, MCP, or LLM serving infrastructure.
* Experience with AWS Bedrock and AI infrastructure.
* Prior experience in a regulated industry or enterprise environment with formal compliance requirements.

Minimum Requirements

Minimum Education: Bachelor's degree in Computer Science, Information Technology, or a related field, or equivalent practical experience
Minimum Experience: 3 or more years of experience in Platform Engineering, DevOps, or Cloud Operations
Required Technical Skills: Must have at least 3 years of experience with Databricks administration in a production environment, Terraform or equivalent infrastructure-as-code tooling, AWS services including S3, IAM, and VPC, and Python or Bash scripting for automation Candidates must be willing to participate in at least one in-person interview.