Description

You will design, deploy, and manage production-grade AI infrastructure on AWS, focusing on Kubernetes, LLM operations, and agent-based systems.

This role is on-site.

Responsibilities

• Deploy, manage, and troubleshoot Kubernetes clusters, including disconnected installations.
• Design, deploy, and upgrade Amazon EKS clusters in production environments.
• Implement and manage LLMOps workflows, including deployment, monitoring, and scaling of Generative AI systems.
• Build and maintain agent-based workflows using frameworks like LangChain, CrewAI, or AutoGen.
• Design and optimize Retrieval-Augmented Generation (RAG) pipelines for performance and scalability.

Required Skills

• Strong Kubernetes expertise (installation, administration, troubleshooting).
• Extensive hands-on experience with Amazon EKS (deployment, upgrades, troubleshooting).
• Proven experience with LLMOps and production-grade Generative AI systems.
• Experience with agentic AI frameworks (LangChain, CrewAI, AutoGen).
• Hands-on experience with vector databases (e.g., Pinecone, Weaviate, Milvus) and RAG architectures.
• Knowledge of AI governance, security guardrails (e.g., NeMo Guardrails), and cost control for LLMs.
• Experience building AI-focused Internal Developer Platforms (IDP).

Key Skills

Education

Any Gradute