Senior Staff Engineer (Cloud)

REQUIREMENTS:

• Experience : 7.5+ Years
• 10-12 years in infrastructure, platform, DevOps, or MLOps roles
• Strong experience with cloud platforms (AWS/GCP/Azure) and Kubernetes
• Hands-on experience deploying and operating LLMs (OpenAI, Anthropic, open-source models)
• Proficiency with GPU infrastructure, model serving frameworks, and vector databases
• Strong programming skills in Python; experience with Bash/Go is a plus
• Experience with monitoring, logging, and performance tuning for distributed systems
• Preferred Qualifications
• Experience with LLM fine-tuning, RAG pipelines, and prompt/version management
• Familiarity with tools like Terraform, Helm, Argo, Ray, or similar
• Exposure to cost optimization strategies for large-scale AI systems

Responsibilities:

• Design and manage scalable infrastructure for training, fine-tuning, serving, and monitoring LLMs
• Build and maintain LLMOps pipelines (deployment, versioning, rollback, monitoring, evaluation)
• Optimize inference performance (latency, throughput, cost) across GPU/accelerator stacks
• Implement CI/CD, IaC, and automation for AI/ML workloads
• Ensure observability, reliability, and governance of LLM systems in production
• Collaborate with ML, platform, and product teams to operationalize AI solutions
• Manage security, compliance, and access control for model and data pipelines

Bachelor’s or master’s degree in computer science, Information Technology, or a related field.