DevOps Engineer

CosMicIT is seeking a Staff Platform Engineer, AI/ML Infrastructure to provide technical leadership for the cloud platforms, deployment systems, and operational foundations supporting enterprise-scale generative AI applications. The role focuses on designing and operating AWS and Kubernetes infrastructure, establishing infrastructure-as-code and CI/CD standards, improving observability and security, and mentoring engineers across platform teams.

Responsibilities:

• Define and drive the technical strategy for AI/ML platform infrastructure supporting generative AI applications, LLM integrations, model routing, and enterprise AI services
• Architect, build, and operate scalable cloud platforms using AWS services such as EKS, ECS Fargate, Lambda, DynamoDB, S3, OpenSearch, Secrets Manager, CloudWatch, ALB, and MWAA
• Establish reusable infrastructure patterns using CloudFormation, Helm, and Terraform to support reliable multi-environment and multi-region deployments
• Lead CI/CD architecture using GitHub Actions, reusable workflows, OIDC-based AWS authentication, automated quality gates, deployment promotion, and environment approvals
• Design and improve observability across AI platforms, including CloudWatch dashboards, logs, alarms, Prometheus/Grafana, OpenSearch, Langfuse, and LLM-specific operational metrics
• Build platform capabilities for GenAI workloads, including model availability monitoring
• Partner with software engineering teams to improve deployment reliability, rollback strategies, health checks, autoscaling, load testing, and runtime performance
• Define and enforce security and compliance practices for infrastructure, including IAM permission boundaries, Secrets Manager usage, secret scanning, audit logging, tagging standards, and change-management controls
• Provide technical leadership for cost optimization, capacity planning, environment standardization, and operational resilience across development, test, production, and sandbox environments
• Mentor engineers, review architecture and infrastructure designs, and influence platform engineering practices across teams
• Troubleshoot complex production issues across cloud infrastructure, networking, containers, serverless workloads, CI/CD systems, and observability platforms
• Translate enterprise requirements for security, compliance, reliability, and governance into pragmatic engineering standards and automation

Requirements:

• • Bachelorʼs degree in Computer Science, Engineering, Information Technology, or a related technical field, or equivalent practical experience
• • 7+ years of experience in DevOps, platform engineering, cloud infrastructure, site reliability engineering, or software engineering roles
• • Strong hands-on experience with AWS/Azure/GCP infrastructure and services, including container, serverless, networking, storage, observability, and security services
• • Experience designing and operating production systems on Kubernetes, ECS/Fargate, or comparable container orchestration platforms
• • Proficiency with infrastructure-as-code, especially CloudFormation, Terraform, Helm, or similar tooling
• • Strong CI/CD experience with GitHub Actions or similar platforms, including reusable workflows, automated testing, deployment gates, and cloud authentication
• • Experience building and operating observability solutions using CloudWatch, Prometheus/Grafana, OpenSearch, or similar tools
• • Strong understanding of cloud security practices, IAM, secrets management, least-privilege access, audit logging, and compliance requirements
• • Experience supporting distributed systems, microservices, APIs, asynchronous workloads, and multi-environment deployments
• • Demonstrated ability to lead technical design, mentor engineers, and influence engineering practices across teams
• • Experience supporting AI/ML or generative AI platforms, including LLM gateways, model routing, prompt observability, token metering, or model failover
• • Experience operating platforms in regulated enterprise environments, ideally healthcare, pharmaceutical, finance, or life sciences
• • Experience with multi-account, multi-region AWS architectures and enterprise governance patterns
• • Experience with cost optimization, autoscaling strategies, capacity planning, and cloud budget monitoring
• • Experience with load testing and performance validation using tools such as Locust or comparable frameworks
• • Strong Python or scripting skills for platform automation, operational tooling, and CI/CD extensions
• • Ability to communicate complex technical decisions clearly to engineering, security, operations, and leadership audiences