Senior DevOps / MLOps Engineer

This is a fully remote position, open to applicants in Maryland.

📋 Description

• Deploy and manage SimpliGov’s Azure platform, encompassing AKS, networking, identity, storage, and environments from development to production.

• Take ownership of infrastructure as code from start to finish, ensuring environments are reproducible, drift detection is in place, and all changes to the platform are visible.

• Operate the AI infrastructure layer, which includes self-hosted observability and evaluation tools, product telemetry, model gateway, per-workload routing, and compliant GovCloud inference paths.

• Oversee cloud and AI cost metering, budgets, unit economics, MACC drawdown strategy, and remediation efforts.

• Strengthen production access and controls by implementing least privilege, managing secrets, providing audit evidence, and maintaining a FedRAMP-conscious security posture.

• Collaborate with AI Operations on deployment and release workflows using Octopus Deploy, including environment promotion, progressive rollout, and rollback strategies.

• Enhance platform reliability through effective monitoring, alerting, incident response, and capacity planning.

• Facilitate microservices decomposition with appropriate service infrastructure, scaling patterns, and clear environment boundaries.

• Engage in an AI-native product development lifecycle that involves autonomous agents in planning, coding, validation, and release processes.

• Take full responsibility for everything that is shipped and proactively address uncertainties early on.

⛳️ Requirements

• Over 5 years of experience in DevOps, platform engineering, or site reliability engineering within SaaS environments.

• Extensive experience with Azure, including AKS, networking, Entra identity, and monitoring tools.

• Proven experience in managing production Kubernetes environments.

• Proficiency in infrastructure as code as the standard approach, utilizing tools such as Terraform, Bicep, or similar technologies.

• Strong scripting capabilities.

• Experience in MLOps, particularly in deploying and managing LLM or ML systems in a production setting.

• Familiarity with model gateways, inference infrastructure, or AI observability stacks.

• Demonstrated experience in cloud cost analysis and reduction strategies.

• Previous experience in compliance-heavy environments like FedRAMP, StateRAMP, SOC 2, or similar is highly advantageous.

• Comfortable managing production access with the necessary discipline.

• Applicants must not require work visa sponsorship.

• Must fulfill US employment authorization requirements via Form I-9/E-Verify.

🏝️ Benefits

• Comprehensive medical, dental, and vision insurance plans, with significant employer contributions for both employees and their dependents.

• Buyup insurance plans available at additional costs.

• Company-sponsored life and disability insurance coverage.

• 11 paid holidays throughout the year.

• Flexible time off policy.

• 401k plan featuring a 4% employer match.

• Monthly stipends for wellness and home office expenses.

• Bonus opportunities.

• Additional benefits.