AI Engineer (LLM, RAG, Agents)

Role overview Build and operate production AI systems that use large language models, retrieval-augmented generation (RAG), and autonomous agents. The work spans document processing, sales workflow automation, and customer support grounded in private knowledge bases, with success measured by practical business outcomes.

Responsibilities - Develop LLM integrations, prompts, fine-tuning approaches, and evaluation methods for production use. - Design RAG pipelines covering document ingestion, chunking, embeddings, vector indexing, hybrid search, and reranking. - Build agents that use tools, coordinate across multiple agents, and include human review where needed. - Create evaluation workflows and use their results to improve system accuracy. - Deploy guardrails, tracing and observability, and cost controls. - Collaborate with technical stakeholders on architecture decisions and keep current with model and evaluation developments.

Requirements - At least four years building production AI or machine-learning systems. - Strong Python skills, including experience with FastAPI, asynchronous code, and typing; plus TypeScript or Go for service development. - Hands-on work with commercial LLMs and at least one open-source model family. - Production experience with RAG methods, including chunking, embedding selection, hybrid retrieval, and reranking. - Experience using a vector database in production and an orchestration framework such as LangChain, LlamaIndex, or LangGraph. - Cloud deployment experience on AWS or GCP, Docker, observability tools, and business-level English for writing, reviews, and client discussions.

Nice to have Experience with evaluation tooling such as RAGAS, tracing platforms, and custom evaluation systems.