AI Engineer

Role Overview

Heu.ai is seeking a hands-on AI / LLM Engineer to design, build, and deploy intelligent system architectures and agentic workflows. You will go beyond simple wrapper scripts to build production-grade Retrieval-Augmented Generation (RAG) pipelines, complex multi-agent orchestrations, and robust backend APIs.

Responsibilities

• Design and deploy stateful, multi-agent orchestrations and dynamic decision-making graphs using LangGraph.
• Build, evaluate, and optimize hybrid retrieval strategies including vector search, BM25, and reranking.
• Architect and iterate on structured prompts and establish evaluation frameworks to monitor quality and hallucination rates.
• Develop scalable, asynchronous REST/gRPC APIs and microservices using FastAPI or Flask.
• Manage and optimize vector databases such as Pinecone, Qdrant, Chroma, or PGVector.
• Monitor latency, token usage, and implement caching strategies for low-latency experiences.

Requirements

• 1-3 years of experience in AI/LLM engineering.
• Strong proficiency in Python with an emphasis on async programming and clean architecture.
• Demonstrated experience with LangGraph, LangChain, or custom agentic execution systems.
• Proven experience implementing end-to-end RAG workflows.
• Solid background in building production APIs via FastAPI or modern web frameworks.
• Experience with structured outputs using JSON schema and Pydantic.
• Experience with fine-tuning open-source models like Llama or Mistral or using Ollama and vLLM.

Skills

• Python
• LangChain
• RAG
• FastAPI
• Vector Databases