ML Engineer - RAG Systems

about this role

Build and optimize retrieval-augmented generation systems for enterprise customers. Work on vector search, embedding models, and production RAG pipelines.

responsibilities

• •Design and implement RAG architectures
• •Optimize vector search performance
• •Develop evaluation frameworks for retrieval quality
• •Create customer-facing documentation and examples
• •Support enterprise customer implementations

requirements

• 3+ years of ML engineering experience
• Experience with vector databases and embeddings
• Strong Python and software engineering skills
• Understanding of transformer architectures
• Experience with production ML systems

nice to have

• +Experience with LangChain or similar frameworks
• +Contributions to open-source ML projects
• +Background in information retrieval

benefits