AI Engineer

Job Summary

Specializing in production-grade LLM and RAG architectures, the remote AI Engineer will build, deploy, and optimize advanced AI applications that transform unstructured data into actionable insights while collaborating internationally on high-impact projects.

Key responsibilities

• Architect and implement robust LLM-powered conversational agents with advanced function-calling and dialogue state management
• Design and build high-precision RAG pipelines, including indexing, chunking, and hybrid retrieval mechanisms
• Develop document intelligence solutions to ingest, parse, and analyze complex PDFs using OCR and multimodal LLMs

Required qualifications

• Minimum 3 years of experience developing and deploying ML/AI applications in production, with 1-2+ years focused on LLMs and RAG systems
• Strong Python programming skills and hands-on expertise with frameworks like LangChain and Hugging Face
• Proven experience with vector databases and semantic search techniques
• Deep knowledge of document processing, including OCR and layout parsing
• Experience with cloud deployment on AWS, Azure, or GCP, including CI/CD pipelines