Senior AI Engineer (LLM, RAG & Agentic AI Systems)

We are looking for a highly skilled AI Engineer with hands-on experience building production-grade Large Language Model (LLM) applications, Retrieval-Augmented Generation (RAG) systems, and AI Agents. The ideal candidate has experience designing scalable AI solutions, fine-tuning open-source models, implementing advanced RAG pipelines, and deploying AI applications into production environments. Responsibilities: - Design and develop LLM-powered applications using OpenAI, Claude, Llama, Mistral, and similar models. - Build end-to-end RAG pipelines including document ingestion, embeddings, chunking, vector databases, retrieval optimization, and response generation. - Develop AI Agents with tool calling, function calling, MCP integrations, and multi-agent workflows. - Implement OCR and document intelligence solutions for structured and unstructured data. - Fine-tune LLMs using PEFT techniques such as LoRA and QLoRA. - Deploy and optimize models using vLLM, llama.cpp, and other inference frameworks. - Build scalable APIs and AI microservices using Python or Node.js. - Manage Docker, Kubernetes, CI/CD pipelines, and cloud deployments. - Monitor, evaluate, and improve LLM and RAG performance. Required Skills: LLMs, RAG, AI Agents & Agentic Workflows, LangChain, LangGraph, LlamaIndex, Vector Databases, Prompt Engineering, Fine-Tuning, Python, OpenAI API, Anthropic Claude API, Docker, Kubernetes, MLOps, OCR & Document Processing Preferred Qualifications: - Experience with multilingual NLP projects. - Experience deploying open-source models in production. - Strong understanding of AI evaluation frameworks and observability. To Apply Please include: 1. Examples of LLM or RAG systems you've built. 2. AI Agent or workflow automation projects completed. 3. Tech stack used. 4. Hourly rate and availability. 5. Relevant case studies or GitHub links.