Applied AI Engineer

About the job

Job Title : Applied AI Engineer (AI/ML & LLM Deployment) Experience : 4+ Years Location : Remote Job Summary : We are looking for an Applied AI Engineer with strong expertise in Large Language Models (LLMs) to design, optimize, and deploy advanced AI solutions. The role focuses on LLM integration, fine-tuning, and performance optimization for scalable production use. Mandatory Skills : LLM Integration, Prompt Engineering, LangChain/LlamaIndex, Fine-tuning & LoRA, Model Quantization, Local Deployment, Tokenizers, Performance Optimization. Key Responsibilities : • Integrate GPT-4, Claude, and open-source LLMs into applications. • Design and implement prompt engineering for context-specific, tone-appropriate outputs. • Build AI pipelines using LangChain, LlamaIndex, or similar frameworks. • Perform fine-tuning and LoRA (Low-Rank Adaptation) to customize models. • Apply model quantization (GGML, GPTQ, bitsandbytes) for efficient deployment. • Deploy models with Hugging Face Transformers, vLLM, llama.cpp. • Optimize tokenization and inference performance for low latency. Required Skills : • Strong hands-on experience with LLMs (OpenAI GPT-4, Claude, open-source models). • Proficiency in Prompt Engineering and tone-specific output design. • Experience with LangChain, LlamaIndex, or other orchestration frameworks. • Knowledge of fine-tuning, LoRA techniques, and quantization methods. • Familiarity with deployment frameworks (Transformers, vLLM, llama.cpp). • Strong understanding of tokenizers and efficient text preprocessing. • Ability to optimize models for real-time, low-latency inference. • Solid programming skills in Python and experience with PyTorch/TensorFlow. Nice to Have : • Exposure to MLOps tools (Docker, Kubernetes, CI/CD for AI). • Experience with evaluation frameworks for LLMs. • Knowledge of multi-modal models (text, vision, audio).

Requirements

• LLM Integration
• Prompt Engineering
• LangChain/LlamaIndex
• Model Quantization
• Performance Optimization

Preferred Technologies

• LLM Integration
• Prompt Engineering
• LangChain/LlamaIndex
• Model Quantization
• Performance Optimization