Artificial Intelligence Engineer - LLM/RAG

Key Responsibilities :

- Develop and maintain LLM-powered applications using Microsoft Agent Framework, AutoGen, LangChain, LangGraph, and LlamaIndex

- Design and optimize Retrieval-Augmented Generation (RAG) pipelines including chunking strategies, embeddings, and vector database management

- Build autonomous AI agents with multi-step planning and human-in-the-loop workflows

- Perform model fine-tuning and optimization using Quantization, PEFT, and LoRA techniques

- Deploy AI models in production using Docker and Kubernetes ensuring scalability and low latency

- Monitor AI systems for hallucinations, latency, accuracy, and cost optimization with strong observability practices

- Maintain ML CI/CD pipelines with automated testing and model-quality validation

- Collaborate with Architects and Engagement Managers to convert business requirements into scalable AI solutions

Required Skills :