Description :
Job Title : AI Automation Engineer (LLM Workflows)
Location : Remote (India)
Experience : 3+ years
About the Role :
We are seeking a highly skilled AI Automation Engineer with deep expertise in Large Language Models (LLMs) and automation workflows.
In this role, you will design, build, and deploy intelligent automation solutions leveraging state-of-the-art LLMs (e.g., GPT, Claude, Mistral) to enhance internal operations, streamline customer support, and optimize knowledge management processes.
You will work at the intersection of AI engineering, automation, and systems integration, creating AI-powered copilots and RAG pipelines that empower teams with real-time insights and data-driven decision-making.
Key Responsibilities :
LLM Application Development :
- Design, implement, and maintain GPT- and Claude-based assistants for business automation, support, and internal operations.
- Build and optimize LLM-powered copilots using frameworks such as OpenAI Assistant API, Lovable, and LangChain.
Data Retrieval & Automation Pipelines :
Develop Retrieval-Augmented Generation (RAG) pipelines to enable dynamic querying of financial data, business reports, and structured / unstructured datasets.Ensure efficient data access, indexing, and relevance scoring using vector databases like Weaviate, Chroma, or Pinecone.Systems Integration :
Integrate LLMs with internal tools and platforms such as Notion, Slack, Google Workspace, and other enterprise systems for task automation and insight generation.Develop APIs and workflow automations that allow seamless interaction between AI systems and existing infrastructure.LLM Orchestration & Optimization :
Build and manage LLM orchestration pipelines using frameworks such as LangGraph or LlamaIndex.Implement advanced prompt engineering, tool calling, and agent memory techniques for efficient and context-aware AI behavior.Performance Monitoring & Continuous Improvement :
Monitor system performance, evaluate model outputs, and fine-tune prompts and pipelines for accuracy, efficiency, and reliability.Stay up to date with advancements in AI automation, agentic workflows, and enterprise AI tools.Required Qualifications :
3+ years of experience in software engineering or AI automation roles.Strong proficiency in Python and experience with LLM APIs (OpenAI, Anthropic Claude, Mistral).Hands-on experience with vector databases (Weaviate, Chroma, Pinecone) for RAG implementations.Proven ability to build and deploy custom GPT Assistants and LLM orchestration pipelines (LangChain, LangGraph, LlamaIndex).Deep understanding of prompt engineering, tool / function calling, and agent memory management.Strong problem-solving skills, with a focus on automation, optimization, and real-world AI deployment(ref : hirist.tech)