Description

Design and deploy multi-agent AI systems, LLM applications, and RAG pipelines for enterprise integration.

This role is remote.

Responsibilities

• Build and maintain RAG pipelines, vector databases, and autonomous business workflows.
• Develop LLM-based applications using LangChain, LlamaIndex, and Hugging Face ecosystem.
• Integrate LLMs with external systems via APIs and manage stakeholder communication on AI capabilities.
• Perform LLM fine-tuning, prompt engineering, and model performance optimization in production.
• Produce AI system architecture and technical design documentation for engineering teams.

Required Skills

• Python with FastAPI or Flask for backend development.
• Experience with LangChain, LlamaIndex, Transformers, and PyTorch.
• Knowledge of OpenAI API, Azure OpenAI, Anthropic Claude, AWS Bedrock, or Google Vertex AI.
• Proficiency with vector databases: Pinecone, Weaviate, or ChromaDB.
• JavaScript or TypeScript for AI frontend integration.
• Experience with Git, Docker, and Kubernetes for deployment.
• SQL/NoSQL database management and MLOps practices.
• 6+ years of engineering experience.

Preferred Skills

• Knowledge graphs and enterprise knowledge management systems.
• Experience with AI agent orchestration, planning algorithms, and decision-making frameworks.

Key Skills

Education

Bachelor's degree