Description

You will own the reliability, scalability, and automation of large-scale AI infrastructure and LLM workloads.

This role is on-site.

Responsibilities

• Design and maintain highly available Kubernetes infrastructure for LLM training, fine-tuning, and inference.
• Architect and deploy multi-agent GenAI systems to automate alert triage, root cause analysis, and self-healing remediation.
• Optimize GPU orchestration, cluster health, and compute utilization across large-scale environments.
• Define and monitor non-traditional SLOs/SLIs, including Time-to-First-Token (TTFT), Inter-Token Latency, and cost-per-query limits.
• Integrate LLMs and agentic frameworks into ChatOps tooling for real-time incident assistance.

Required Skills

• 5+ years of experience in SRE or DevOps roles.
• Deep expertise in Kubernetes (EKS/GKE), Terraform, and CI/CD pipelines.
• Strong proficiency in Python or Go for building tool integrations via APIs and Model Context Protocol (MCP).
• Hands-on experience with LLM orchestration frameworks such as AutoGen, LangChain, or LlamaIndex.
• Experience managing distributed vector databases (e.g., Pinecone, Milvus, Qdrant, or pgvector).
• Advanced knowledge of cloud monitoring stacks (Datadog, Prometheus, OpenTelemetry) applied to AI workloads.

Preferred Skills

• Bachelor's degree in Computer Science or related field.
• Experience implementing infrastructural guardrails to protect LLM endpoints from prompt injections and data leaks.

Key Skills

Education

Bachelor's degree