Job Description: AI Engineer – On-Premises AI, LLM & Infrastructure
Experience: 1–5 Years
Employment Type: Full time

Job Overview
We are looking for an AI Engineer with hands-on experience in developing, deploying, and optimizing AI applications on on-premises infrastructure. The candidate should have knowledge of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), intent parsing, tool calling, Model Context Protocol (MCP), AI orchestration, and GPU-accelerated computing.
The role involves working with locally hosted AI models and NVIDIA GPU infrastructure, including NVIDIA RTX 6000 Blackwell and L40S. The candidate will also be responsible for application containerization, Microsoft Hyper-V virtualization, performance optimization, scalability, networking, security, and maintaining reliable on-premises AI environments.
The ideal candidate should be capable of taking AI applications from development and experimentation through deployment, optimization, and production maintenance.

Key Responsibilities
1. LLM Deployment & On-Premises AI
• Deploy, configure,



and manage locally hosted LLMs such as Qwen, Mistral, Kimi, and other suitable open-weight models.
• Work with inference frameworks such as Ollama, vLLM, and similar model-serving technologies.
• Deploy AI workloads on NVIDIA RTX 6000 Blackwell, L40S, and compatible GPU infrastructure.
• Optimize model inference, GPU utilization, VRAM consumption, response latency, and throughput.
• Evaluate model performance, tool-calling capabilities, accuracy, and hardware requirements.
• Implement quantization, batching, streaming inference, and other optimization techniques where appropriate.
• Troubleshoot GPU drivers, CUDA compatibility, memory allocation, and model-serving issues.
• Maintain local AI deployments with an emphasis on data governance, privacy, and reduced dependence on external AI services.

2. RAG, Intent Parsing & AI Orchestration
• Develop RAG pipelines for retrieving information from docu

📌 AI Engineer – On-Premises AI, LLM (Coimbatore)
🏢 AppXcess Technologies
📍 Coimbatore