Lead GCP DevOps Engineer; AI-Enabled Platform

About the role

In this role, you will design and evolve cloud-native platforms on Google Cloud Platform, helping global organizations modernize infrastructure, accelerate software delivery, and improve operational resilience.

Working within our Cloud and Dev Ops Practice, you’ll collaborate with experienced engineers and architects to deliver secure, scalable, and AI-ready solutions while shaping engineering best practices across projects.

• Design, build, and operate scalable, secure, and reliable cloud infrastructure on Google Cloud Platform
• Lead or support migration initiatives from other clouds to GCP, ensuring service continuity, security, and cost optimization
• Build, maintain, and continuously improve CI/CD pipelines and deployment automation
• Develop and manage infrastructure using Terraform and Infrastructure as Code best practices
• Deploy, manage, and optimize containerized applications using Kubernetes and Docker
• Implement monitoring, logging, and alerting solutions to ensure platform reliability and performance
• Collaborate with software engineers, architects, and AI/ML teams to deliver cloud-native and AI-enabled solutions
• Support GPU-based infrastructure and AI workloads where applicable
• Implement cloud security best practices, including IAM, secrets management, encryption, and vulnerability management
• Troubleshoot complex production issues and drive continuous platform improvements
• Share technical expertise, mentor team members, and contribute to architecture and engineering best practices

• Strong hands‑on experience in Dev Ops, Platform Engineering, or Site Reliability Engineering
• Proven experience designing, implementing, and operating solutions on Google Cloud Platform (GCP)
• Strong experience with Kubernetes (GKE preferred) and Docker in production environments
• Experience building and maintaining CI/CD pipelines using Git Hub Actions, Argo CD, or similar CI/CD tools
• Hands‑on experience with Infrastructure as Code tooling
• Solid understanding of cloud networking, including Virtual Networks, DNS, load balancing, IAM, VPNs, and security best practices
• Experience implementing monitoring, logging, and observability solutions (e.g., Prometheus, Grafana, Datadog, or similar tools)
• Proficiency in scripting and automation using Python, Go, or Bash
• Strong troubleshooting and problem‑solving skills across cloud infrastructure and distributed systems
• Upper‑Intermediate or higher English level for effective communication in a global environment
• Experience supporting AI‑enabled platforms or machine learning infrastructure and/or familiarity with Vertex AI, Kubeflow, MLflow, Ray, or similar AI/ML platforms
  * would be appreciated)
• Familiarity with NVIDIA technologies, including GPU-enabled infrastructure, NVIDIA GPU Operator, CUDA, or NVIDIA AI Enterprise (nice to have)
• Experience providing technical leadership, mentoring engineers, and driving technical decisions (would be an advantage)
• Experience migrating enterprise workloads between clouds (is a plus)
• Experience in designing infrastructure architectures (would be desirable)

Soft Serve is an equal opportunity employer. Qualified applicants will receive consideration regardless of race, color, ancestry, ethnicity, national origin, religion, sex, sexual orientation, gender identity or expression, age, citizenship, disability, health condition, marital or family status, veteran status, or any other characteristic protected by applicable law.

Work from home, from the office, or in a hybrid format that supports focus and collaboration.

Competitive, market-based pay, benchmarked by role and location — plus health coverage, paid time off, wellness support, and learning opportunities.

Approachable leaders who communicate openly, keep teams close to the strategy, and support long‑term planning.