AI Engineer
Core
Design and implement end-to-end RAG pipelines, agentic workflows, and LLM integrations for enterprise clients.
Role type
Mid-level AI Engineer (LLM/RAG)
Builds
Production-grade AI systems, RAG pipelines, agentic workflows, MCP servers
Domain
Enterprise AI, Large Language Models, Retrieval-Augmented Generation
Deliverable
production ML models
Required skills
Python, RAG pipeline design, agentic workflow orchestration, LLM integration and prompt engineering, vector database management, evaluation pipeline development, Docker
Preferred skills
MCP protocols, knowledge graphs, inference optimization (quantization, vLLM), evaluation tooling (RAGAS, TruLens), domain NLP in legal/manufacturing/healthcare
Technologies
LangChain, LangGraph, LlamaIndex, FAISS, Pinecone, Weaviate, Qdrant, pgvector, Docker, Python
Responsibilities
Design and implement RAG pipelines end-to-end; Build agentic workflows using LangChain, LangGraph, or custom orchestration; Integrate and prompt-engineer LLMs; Develop MCP servers and clients; Maintain vector databases and optimize retrieval quality; Build evaluation pipelines to track hallucination and latency; Write clean, tested, production-ready Python
Seniority
Mid-level, hands-on IC