Location: Tampa, FL (Onsite)
Duration : 6+ Months

Job Summary

We are seeking an experienced AI Reliability Engineer (SRE) to design, deploy, and maintain highly available infrastructure supporting GenAI and Large Language Model (LLM) workloads. The ideal candidate will have strong expertise in Kubernetes, AI infrastructure, observability, automation, and modern GenAI frameworks.

Key Responsibilities:

• Design, scale, and maintain reliable infrastructure for LLM training, fine-tuning, and inference workloads.
• Architect and implement agentic AI systems for alert triage, root cause analysis, and self-healing operations.
• Manage GPU orchestration, cluster health, and compute utilization across Kubernetes environments.
• Define and monitor AI-specific SLOs and SLIs such as Time-to-First-Token (TTFT), latency, and cost-per-query metrics.
• Support vector databases and RAG pipelines to ensure reliability and performance.
• Implement security controls and guardrails to protect LLM applications from prompt injection, hallucinations, and data leakage.
• Automate operational processes and improve infrastructure reliability.

Required Skills:

• Strong experience with Kubernetes (EKS/GKE).
• Expertise in Infrastructure as Code using Terraform.
• Experience with CI/CD pipelines and DevOps practices.
• Proficiency in Python or Go.
• Hands-on experience with LLM frameworks such as LangChain, LlamaIndex, or AutoGen.
• Experience with vector databases including Pinecone, Milvus, Qdrant, or pgvector.
• Knowledge of monitoring tools such as Datadog, Prometheus, and OpenTelemetry.
• Strong understanding of AI infrastructure, automation, and observability.

Preferred Qualifications:

• Experience implementing semantic caching solutions.
• Knowledge of AI cost optimization strategies.
• Experience converting operational runbooks into automated workflows.
• Background supporting large-scale AI and machine learning platforms.