DevOps Engineer

DevOps Engineer (AI-Native Track)

About the Engagement

You will join the Nestingale delivery team to build and operate the infrastructure powering our applied-AI initiatives (LLM/RAG and GenAI workloads). This role bridges conventional DevOps with AI-native engineering, transitioning from standard platform operations to managing model serving, inference pipelines, GPU provisioning, and observability for large language models.

What You'll Do

• Build & Run Infrastructure: End-to-end management of CI/CD pipelines, IaC (Terraform), containers, deployments, and monitoring systems.
• Maintain Reliability: Ensure production health by optimizing for latency, cost, security, and rapid incident response.
• Pioneer AI Workloads: Stand up the infrastructure behind GenAI models, including GPU provisioning, evaluation frameworks, and automated observability stacks.
• Automate Operations: Partner with product and engineering teams to automate workflows using AI agents and copilots.

Who You Are

We are looking for a DevOps/SRE professional with 3–5 years of hands-on experience who thrives in system design, latency optimization, and cost management. You must enjoy debugging complex issues that cause slowness or flakiness.

• Core Requirements:
• Proven production experience building infrastructure for real users using Terraform (or equivalent) on AWS/GCP/Azure.
• Mastery of Docker, Kubernetes, CI/CD tools (GitHub Actions / GitLab CI), and scripting in Python, Go, or Bash.
• A strong appetite for AI-native engineering concepts like LLMOps, MLOps, agentic automation, and FinOps.

Nice to Have

Experience with Vertex AI, MLflow, LangChain, vector databases, GPU infrastructure management, or specific GenAI governance practices.