Job Summary
We are looking for an AI Engineer who can quickly build and ship AI-powered applications using LLMs, RAG, and AI agents.
The role focuses on hands-on development, fast experimentation (vibe coding), and building production-ready AI systems, not just research.
Key Responsibilities
- Design and develop LLM-based AI applications
- Build RAG (Retrieval-Augmented Generation) systems for accurate AI responses
- Design and implement AI agents and multi-agent workflows
- Build AI copilots, chatbots, automation tools, and intelligent assistants
- Integrate AI systems with APIs, databases, and external tools
- Implement document ingestion, chunking, embedding, and retrieval pipelines
- Optimize prompts, retrieval quality, latency, and accuracy
- Rapidly prototype ideas and convert them into production-ready features
- Ensure reliability, security, and scalability of AI applications
- Collaborate with product, backend, and data teams
Desired Profile
- Strong Python programming
- Hands-on experience with Pandas, NumPy, and ML libraries
- Strong experience working with Large Language Models (LLMs)
- Solid understanding of RAG architecture and workflows
- Experience with document ingestion, chunking, and embeddings
- Hands-on experience with vector databases
- Experience building AI agents and tool-based workflows
- Strong understanding of prompt engineering and prompt optimization
- Experience integrating AI with APIs, databases, and tools
- Ability to build production-ready AI services
- Experience with LangChain, CrewAI, AutoGen, or similar frameworks
(ref:hirist.tech)
