Job highlights

- Education Must be from an engineering background or have strong,demonstrable knowledge of AI

- Hands-on experience with LangChain,LlamaIndex,vector databases

- Experience with GPUs,fine-tuning,or training workflows

About the Role Refrens is building advanced AI assistants for invoicing, proposals, client workflows, and business automation. As a Generative AI Engineer, you will build, fine-tune, and optimize LLM-based systems. What Youll Do

- Build AI applications: chatbots, copilots, invoice assistants, document AI, and autonomous agents

- Implement RAG using embeddings and vector databases

- Fine-tune or adapt open-source LLMs (Llama, Mistral, Qwen, etc.)

- Optimize for performance: inference speed, accuracy, and hallucination reduction





- Develop evaluation frameworks and data pipelines

- Build internal tools for automation, testing, and monitoring

What You Need

- Strong Python skills

- Hands-on experience with LangChain, LlamaIndex, vector databases

- Solid understanding of prompting, embeddings, and sampling techniques

- Experience with GPUs, fine-tuning, or training workflows

- Ability to ship fast, debug quickly, and iterate rapidly

Education Must be from an engineering background or have robust, demonstrable knowledge of AI.

📌 LLM / Generative AI Engineer (Surat)
🏢 Refrens.com
📍 Surat