Apply Now

Generative AI Engineer

Build and optimize RAG (Retrieval Augmented Generation) pipelines and prompt engineering workflows.

As a Generative AI Engineer, you will design, build, and optimize applications powered by large language models (LLMs). You'll specialize in Retrieval-Augmented Generation (RAG) systems, prompt engineering, and integrating generative AI into real-world workflows.

Responsibilities

• Develop RAG architectures combining LLMs with vector databases (Pinecone, FAISS).
• Design and optimize prompts to enhance model outputs (prompt engineering).
• Integrate OpenAI APIs, Hugging Face models, or self-hosted LLMs.
• Implement conversation memory and dynamic chaining using LangChain or similar frameworks.
• Evaluate, test, and improve generative model responses.
• Document prompt libraries, pipelines, and optimization strategies.

Requirements

• 2+ years working with LLMs, NLP models, or Generative AI systems.
• Hands-on experience with OpenAI, Hugging Face, LangChain, or similar.
• Strong understanding of RAG concepts and vector search.
• Familiarity with Pinecone, Weaviate, or Chroma.
• Creative thinking and strong experimentation skills.
• Experience with fine-tuning and evaluation metrics for generative models is a plus.