AI Engineer (LLM, RAG, Agents)

Role overview Design and deliver production AI systems built around large language models, retrieval-augmented generation (RAG), and autonomous agents. Applications include document processing, sales workflow automation, and customer support grounded in private knowledge sources, with success measured by operational value and system quality.

Responsibilities - Build LLM services, including model integration, prompt design, fine-tuning, and evaluation. - Develop RAG pipelines covering document ingestion, chunking, embeddings, indexing, hybrid retrieval, and reranking. - Create tool-using agents and multi-agent workflows with human review checkpoints. - Establish evaluation processes and use results to improve accuracy. - Deploy guardrails, tracing, observability, and cost controls for production systems. - Work with client technical leads on architecture choices and keep current with changes in models and evaluation methods.

Requirements - At least four years building production AI or machine-learning systems. - Strong Python skills, including asynchronous services and typing, plus TypeScript or Go experience. - Hands-on work with commercial LLMs and at least one open-source model. - Production RAG experience, including chunking, embedding selection, hybrid search, and reranking. - Production use of a vector database such as Pinecone, Weaviate, Qdrant, or pgvector. - Familiarity with orchestration frameworks such as LangChain, LlamaIndex, or LangGraph. - Experience deploying on AWS or GCP with Docker and observability tools. - Business-level English for technical writing, code review, and daily client discussions.

Nice to have - Experience with RAG evaluation tools such as RAGAS or custom evaluation pipelines. - Familiarity with tracing and monitoring tools such as LangSmith, Datadog, or Grafana.