AI engineer

This role involves developing generative AI solutions utilizing AWS, specifically focusing on Large Language Models (LLMs), prompt engineering, Retrieval-Augmented Generation (RAG), and agentic AI. The key technologies include n8n and Python libraries like LangChain. Tasks include building LLMs on AWS Bedrock, fine-tuning them on SageMaker, creating prompts using LangChain, developing RAG pipelines, building AI agents with crewai or autogen, implementing workflows in n8n, deploying applications with Docker on ECS/EKS, and monitoring performance with CloudWatch and wandb.

Develop generative AI solutions on AWS, focusing on LLMs, prompt engineering, RAG, and agentic AI using n8n and Python libraries like LangChain. Build LLMs (e.g., Anthropic Claude) on AWS Bedrock with boto3. Fine-tune LLMs on AWS SageMaker using transformers and LoRA. Create prompts with langchain for optimized LLM outputs. Develop RAG pipelines with AWS OpenSearch and langchain. Build AI agents with crewai or autogen on AWS Lambda. Implement agentic workflows in n8n (e.g., n8n.io/workflows/6270). Deploy apps with Docker on Amazon ECS/EKS. Monitor performance with Amazon CloudWatch and wandb.