AI DevOps. Engineer

Expedient; Indianapolis (IN); Hybrid; USD 120,000 - 150,000; Full time

Benefits offered by this job

Three weeks PTO

Parental leave

Top-tier health insurance

401(k) match

Job summary

Expedient is seeking an AI DevOps Engineer to build the framework for agentic workflows, tooling apps, and AI integrations. You’ll own from commit to production with Git-driven CI/CD, IaC, release/config management, and observability for cost‑efficient model-powered systems.

This is a build role focusing on LLMOps—prompts, configs, and integrations—rather than maintaining existing pipelines. Hybrid work in Indianapolis or nearby regions with strong compensation.

Qualifications

• 3–5 years in DevOps, platform engineering, SRE or MLOps/LLMOps.
• Designing Git-based CI/CD pipelines from scratch.
• Infrastructure as Code with Terraform and Helm; GitOps with ArgoCD/Flux.
• Kubernetes administration and automation.
• Observability with Elastic/OpenTelemetry; define alerts and SLOs/SLIs.
• Scripting in Python and Bash; SQL fundamentals.
• Secrets management and SSO/OIDC configuration.

Responsibilities

• Design and build Git-based CI/CD pipelines for apps, agentic workflows, MCP servers, and data connectors.
• Provision and manage Kubernetes clusters and client environments with IaC (Terraform, Helm).
• Manage environment and deployment configuration as code across client deployments.
• Own versioning, environment promotion, release gates, and rollback strategies.
• Build observability backbone with monitoring, tracing, and cost instrumentation.
• Stand up LLMOps pipelines for prompts, evaluations, routing, and token dashboards.
• Maintain governance with approvals, audit trails, and security guardrails.

Skills

Git-based CI/CD

Python

Bash

SQL

LLMOps

Observability

Automation mindset

Tools

Terraform

Helm

ArgoCD

Flux

Kubernetes

Job description

Join Expedient's AI CTRL product team as our AI DevOps Engineer - a senior, hands‑on engineer who will build the framework that manages, configures and ships agentic workflows, tooling applications, and AI integrations to clients quickly, safely, and repeatably. You'll own the path from commit to production: Git-driven CI/CD, infrastructure as code, release and config management, observability, and the LLMOps practices that keep model-powered systems reliable and cost‑efficient.

This is a build role - you won't be maintaining someone else's pipelines, you'll be creating the framework the AI Dev team builds on. Because AI CTRL runs on enterprise model APIs (Anthropic Claude, OpenAI, Google Gemini) with RAG and MCP integrations rather than training custom models, this role is LLMOps-focused: prompts, configs, and integrations are the primary code surface, and the operational challenges are deployment velocity, traceability, cost, and risk at scale.

What You'll Do

• CI/CD Pipelines: Design and build Git-based pipelines that automate build, test, and deploy for Retool apps, agentic workflows, MCP servers, and data connectors.
• Infrastructure as Code: Make the platform reproducible. Use Terraform, Helm, and GitOps (ArgoCD/Flux) to provision and manage Kubernetes (Nutanix NKP) clusters and per-client environments as code.
• Configuration Management: Manage environment and deployment configuration as code across a growing fleet of client deployments.
• Release Management: Own versioning, environment promotion, release gates, and clean rollback.
• Observability & Tracing: Build the monitoring backbone - Elastic/ECK, APM, and telemetry distributed tracing - with deployment health, SLOs/SLIs, and usage/cost instrumentation.
• LLMOps Practices: Stand up prompt and configuration versioning, model/prompt evaluation pipelines, A/B testing, multi-provider traffic routing, and token/cost dashboards.
• Change & Risk Management: Implement controlled-change processes - approvals, audit trails, and guardrails - with compliance-as-code for SOC 2 audit logging, secrets management, and SSO/OIDC configuration.
• Automation Marketplace: Build an internal library of vetted, reusable workflows, connectors, and IaC modules.
• Collaborate & Document: Partner with the AI Dev engineering team on platform standards; write the runbooks, release guides, and architecture docs.

What We’re Looking For

• Experience: 3-5 years in DevOps, platform engineering, site reliability, or MLOps/LLMOps.
• Git-based CI/CD: Designing automated build/test/deploy pipelines from scratch.
• Infrastructure as Code: Terraform and Helm; GitOps with ArgoCD or Flux.
• Kubernetes: Operating and automating clusters (Nutanix NKP or equivalent); namespaces, workloads, container lifecycle.
• Observability: Elastic/ECK, APM, OpenTelemetry tracing; defining alerts, SLOs/SLIs.
• Scripting & Data: Strong Python and Bash; SQL fundamentals.
• Secrets & Identity: Secrets management (Vault or equivalent), SSO/OIDC configuration (Entra ID, Okta, OneLogin).
• LLM APIs: Familiarity with Anthropic Claude, OpenAI, and/or Google Gemini - prompt construction, tool use/function calling, token management.
• RAG & MCP Awareness: Chunking, embedding, vector search, context-window management; Model Context Protocol integrations.
• Builder Mindset: Automation-first, reliability-minded, and strong documentation instincts.

Location & Compensation

• Location: Indianapolis, Cleveland, or Pittsburgh. Hybrid work model.
• Salary: Estimated range of $120,000 to $150,000, based on experience.

Working for Expedient

We prioritize ongoing education and continuous innovation. We offer an exceptional benefits package including three weeks of paid time off, parental leave, top‑tier medical, dental, and vision insurance, and a 401(k) with a generous match.

Expedient is an equal opportunity employer.