AI Engineering

Role Overview

We are looking for an experienced AI Infrastructure & Security Engineer to build, secure, and optimize enterprise-grade AI platforms. In this role, you will deploy and manage large language models such as LLaMA 3.1 70B and Mistral on GPU infrastructure, orchestrate AI agents using Kubernetes, and develop MCP servers to support scalable AI workflows. You will design robust security architectures, implement audit logging, configure vector databases such as ChromaDB and Weaviate, and establish guardrails for safe AI operations. The ideal candidate combines strong expertise in AI infrastructure, platform engineering, Kubernetes, vector databases, and AI security best practices.

Responsibilities

• Deploy, optimize, and manage on-premise LLMs on GPU infrastructure.
• Set up and maintain Kubernetes clusters for AI agent deployments.
• Design and implement secure RBAC and access control frameworks.
• Develop, maintain, and scale MCP servers and AI platform services.
• Configure ChromaDB/Weaviate, including indexing, chunking, and hybrid search tuning.
• Implement AI security controls, audit logging, guardrails, and monitoring pipelines.

Requirements

Expertise You'll Bring:

• Strong experience in Generative AI (GenAI), LLM applications, and AI agent architectures.
• Hands-on expertise with Google ADK, A2A (Agent-to-Agent) Protocol, and Multi-Agent Frameworks.
• Proficiency in Python development and backend system design.
• Experience with Prompt Engineering, structured prompting, and LLM orchestration.
• Knowledge of LangGraph, CrewAI, AutoGen, or similar agentic AI frameworks.
• Strong understanding of MCP (Model Context Protocol), tool integration, and tool registration.
• Experience with Vector Databases (Pinecone, Weaviate, ChromaDB, FAISS, Milvus, etc.).
• Expertise in designing LLM-powered workflows, task delegation, and inter-agent communication.
• Experience implementing JSON Schema Validation, structured outputs, and confidence scoring mechanisms.
• Strong problem-solving skills with experience in AI system design, testing, and optimisation.
• Familiarity with REST APIs, microservices, and cloud platforms (AWS/Azure/GCP) is preferred.