Generative AI Operations Engineer (GenAI Ops)

About the role

We are looking for a motivated Generative AI Operations Engineer to lead the deployment, scaling, and maintenance of our cutting‑edge generative AI models and multi‑agent systems. You will collaborate with data scientists, ML engineers, and software developers to ensure reliable, efficient AI services across major cloud platforms.

Key responsibilities

• Design, implement, and maintain CI/CD pipelines for training, evaluating, and deploying large language models and AI agents.
• Orchestrate complex multi‑agent workflows, ensuring seamless Agent‑to‑Agent communication.
• Integrate AI agents with external tools and APIs using open standards such as the Model Context Protocol (MCP).
• Leverage AI‑powered development tools to accelerate infrastructure code, testing, and troubleshooting.
• Define and manage infrastructure as code (IaC) using Terraform, AWS CDK, CloudFormation, or similar.
• Implement monitoring, logging, and tracing (e.g., OpenTelemetry) for model performance, resource usage, and agent actions.
• Optimize scalability, performance, and cost of model serving and inference services.
• Enforce security best practices and ensure compliance with relevant regulations.

Required profile

• Minimum 3 years of experience in DevOps, SRE, or MLOps roles with a focus on cloud infrastructure.
• Hands‑on experience deploying and operating LLM inference services (vLLM, Triton, TGI, Ray Serve, KServe/Seldon).
• Proven ability to work with cross‑functional AI teams and deliver production‑grade solutions.

Required skills

• Python, Bash scripting
• CI/CD tools: Jenkins, GitLab CI, or cloud‑native equivalents
• Cloud platforms: AWS, GCP, Azure
• IaC: Terraform, AWS CDK, CloudFormation
• Containerization & orchestration: Docker, Kubernetes
• LLM serving frameworks: vLLM, Triton, TGI, Ray Serve, KServe, Seldon
• Observability: OpenTelemetry, logging, monitoring solutions
• Model Context Protocol (MCP) or similar integration standards