Source description
About the role
We're Hiring: Senior Cloud & DevOps Engineer (GCP & AI Infrastructure) Company: LS Digital Group | Experience: 510 Years | Notice Period: Immediate Joiners Preferred | Engagement: Open to Full-Time OR Contract / Consulting | Location: Mumbai / Hybrid LS Digital Group is a global Digital Business Transformation (DBT) network executing a massive AI-native evolution. We need an infrastructure veteran to design lean, budget-conscious deployment strategies for our open-source LLM workloads. What youll do & bring to the table: - GCP Mastery (Required) i.e. deep experience in building secure, scalable environments using core Google Cloud services, serverless infrastructure (Cloud Run), and container orchestration (GKE). - Lean AI/LLMOps setup with hands-on experience configuring cost-optimized LLM hosting architectures (e.g., serverless GPUs, quantized GGUF models on CPUs, Spot VMs, and frameworks like vLLM/Ollama). - AI Observability & SRE to design robust monitoring, logging, and tracing frameworks to seamlessly handle cold starts, track token metrics, and guarantee system reliability. - The "AI Builder" Mindset (Plus) with exposure to AWS/Azure, and a genuine love for leveraging AI tools (Cursor, Claude, Copilot, etc.) to accelerate your own code efficiency. We're Hiring: Senior Cloud & DevOps Engineer (GCP & AI Infrastructure) Company: LS Digital Group | Experience: 510 Years | Notice Period: Immediate Joiners Preferred | Engagement: Open to Full-Time OR Contract / Consulting | Location: Mumbai / Hybrid LS Digital Group is a global Digital Business Transformation (DBT) network executing a massive AI-native evolution. We need an infrastructure veteran to design lean, budget-conscious deployment strategies for our open-source LLM workloads. What youll do & bring to the table: - GCP Mastery (Required) i.e. deep experience in building secure, scalable environments using core Google Cloud services, serverless infrastructure (Cloud Run), and container orchestration (GKE). - Lean AI/LLMOps setup with hands-on experience configuring cost-optimized LLM hosting architectures (e.g., serverless GPUs, quantized GGUF models on CPUs, Spot VMs, and frameworks like vLLM/Ollama). - AI Observability & SRE to design robust monitoring, logging, and tracing frameworks to seamlessly handle cold starts, track token metrics, and guarantee system reliability. - The "AI Builder" Mindset (Plus) with exposure to AWS/Azure, and a genuine love for leveraging AI tools (Cursor, Claude, Copilot, etc.) to accelerate your own code efficiency.
More at LS Digital Group