Senior AI Engineer - RAG & LightRAG Framework Expert - Remote

Overview

We are looking for a highly experienced AI Engineer to lead the design and development of advanced Retrieval-Augmented Generation (RAG) applications using the LightRAG framework. This role requires a deep understanding of natural language processing, large language models (LLMs), and scalable system deployment in cloud environments, particularly Microsoft Azure. This position is ideal for candidates who enjoy building high-impact, production-grade AI systems

In Short

• Architect and implement full RAG pipelines optimized for enterprise-grade use cases.
• Integrate and fine-tune state-of-the-art LLMs into the RAG architecture.
• Develop and manage scalable vector-based search solutions using ChromaDB, PostgreSQL (Vector extensions), or equivalent.
• Build robust and secure AI workflows on Microsoft Azure, leveraging its AI and ML toolsets.
• Optimize performance and latency of AI inference and retrieval mechanisms.
• Work closely with cross-functional engineering and data teams to ensure seamless system integration.
• Participate in code reviews, performance tuning, and system debugging.

Requirements

• 5+ years of experience in AI/ML engineering, including experience in LLM integration.
• Demonstrated experience building or leading RAG-based applications using LightRAG or similar frameworks.
• Strong programming skills in Python.
• Experience working with vector databases and similarity search (ChromaDB, FAISS, Weaviate, PostgreSQL w/ vector).
• In-depth knowledge of Azure AI, including deployments, resource management, and security.
• Strong understanding of transformer models, embeddings, and prompt optimization.
• Excellent problem-solving and communication skills.

Benefits

• Opportunity to work on cutting-edge AI technologies.
• Flexible working hours.
• Collaboration with a talented team of professionals.
• Remote work environment.
• Engagement in high-impact projects.