AI Engineer

We are looking for an AI Engineer to enhance our AI capabilities by fine-tuning existing large language models and implementing cutting-edge Retrieval-Augmented Generation (RAG) systems. This role focuses on leveraging embeddings and vector databases to build AI tools capable of retrieving knowledge from custom documents and delivering accurate, dynamic conversational responses.

Role & responsibilities

• Develop and fine-tune large language models to optimize performance for specific use cases.
• Design and implement text embedding solutions to encode and represent semantic data.
• Build and manage vector databases (e.g., FAISS, Pinecone, Weaviate) for efficient information retrieval.
• Create and deploy Retrieval-Augmented Generation (RAG) pipelines for AI-driven knowledge retrieval.
• Collaborate with cross-functional teams to integrate AI solutions with business tools such as CRMs and internal knowledge bases.
• Test and validate the AI's ability to retrieve and respond using real-world data.
• Stay updated on advancements in RAG, embeddings, and vector database technologies.

Requirements

• Strong experience with large language models (e.g., Llama, GPT, or similar).
• Proficiency in working with embeddings and designing vector databases.
• Hands-on experience with tools like FAISS, Pinecone, or Weaviate.
• Knowledge of retrieval-augmented generation (RAG) pipelines and architecture.
• Expertise in Python and familiarity with frameworks like Hugging Face, TensorFlow, or PyTorch.
• Strong analytical and problem-solving skills, with a focus on real-world application.

Preferred candidate profile

• Experience with fine-tuning LLMs for specific business or operational needs.
• Knowledge of AI integrations with enterprise tools like GitHub, CRMs, or support systems.
• Familiarity with deploying scalable AI solutions in production environments.
• A solid understanding of conversational AI and dynamic response generation.