LLM & Automation Engineer (India)

About the Role We are looking for a creative and pragmatic Mid-Level LLM & Automation Engineer to join our team. In this role, your primary focus will be connecting powerful Large Language Models (LLMs) to real-world business applications through intelligent workflow automation. You will not be building models from scratch, training custom models, or managing complex vector databases for RAG. Instead, you will act as a master orchestratorusing n8n, advanced prompt engineering, and LLM APIs to build highly effective automated systems that save time and unlock new capabilities for our business. What You Will Do Workflow Automation: Design, build, and deploy complex, multi-step automation workflows using n8n, integrating various business systems (CRM, email, internal databases) with LLM capabilities. Prompt Engineering: Craft, iterate, and rigorously test prompts to ensure consistent, accurate, and high-quality outputs from models like GPT-4, Claude 3, or Gemini. API Orchestration: Work extensively with REST APIs, Webhooks, and JSON data to bridge the gap between third-party SaaS platforms and LLMs. Cost & Performance Optimization: Monitor API usage, manage token consumption, and optimize workflows to balance speed, cost, and output quality. Error Handling & Edge Cases: Build robust, fault-tolerant n8n workflows that can gracefully handle API rate limits, hallucinations, and unexpected model outputs. What We Are Looking For Experience: 3+ years in software engineering, automation, or backend development, with at least 12 years of focused experience working with LLM APIs (OpenAI, Anthropic, Google, etc.). Automation Mastery: Deep, hands-on experience with n8n. You should be comfortable building custom HTTP requests, writing expression formulas, and handling data transformations within the platform. Programming Skills: Solid proficiency in JavaScript/TypeScript (highly preferred for n8n node building/Code nodes) or Python. API Expertise: Exceptional understanding of REST APIs, JSON, webhooks, and asynchronous data flows. Problem-Solving: A tinkerers mindset. You enjoy figuring out how to make different software systems "talk" to each other using AI as the reasoning engine. What You DON'T Need (Out of Scope for this Role) We value clarity in our hiring. For this specific role, you will not be expected to know or do the following: No RAG required: You do not need experience with Vector Databases (Pinecone, Milvus), embeddings, or Retrieval-Augmented Generation pipelines. No model training required: You do not need experience with custom model fine-tuning, LoRA, PyTorch, or pre-training AI models. Nice-to-Haves Familiarity with agentic workflows or multi-agent routing using API logic. Experience writing automated tests to evaluate LLM output quality. Compensation: 75,000.00 - 100,000.00 per month Work Location: In person .