Internship Master: Developing a Retrieval-Augmented Virtual Assistant

This internship offers a unique opportunity to gain experience in AI development, making you stand out in the job market. By the end of this internship, you will have:

• Practical experience in Retrieval-Augmented Generation (RAG)
• Hands-on exposure to LLM fine-tuning and deployment in real-world applications
• Experience working with real datasets, preprocessing, and adapting them for AI models
• Skills in model evaluation and optimization
• Collaboration experience within a professional data science team
• A concrete AI project to showcase to future employers, demonstrating your ability to develop solutions for real business challenges
• access to data to train and fine-tune the AI assistant
• compute resources to develop and evaluate AI models
• A collaborative and innovative work environment as part of our data team

Rapid advancements in deep learning technology have led to the rise of Large Language Models (LLMs), which are capable of generating context-aware, human-like responses to queries. While many of such models are publicly available and perform great on general tasks, they often fall short in domain-specific tasks, making them less effective for specialized industries. Developing a domain-specific LLMs from scratch is prohibitively expensive for the majority of companies, which is why a technique called 'Retrieval Augmented Generation' (RAG) has recently gained traction. RAG enhances existing LLMs with data retrieval capabilities, allowing them to pull from sources like technical manuals, internal documentation or even SQL databases to provide more precise, context-aware responses when interacting with a user.

At Bestmix Software, we aim to stay at the forefront of innovation. Because we always look to provide the best services for our customers, our next step is to develop our own virtual assistant to provide customer support, streamline workflows and enhance training programs. To make this vision a reality, we are looking for a motivated master's student with a background in data science to help us build and refine a RAG-powered AI assistant.

We are looking for an enthusiastic master student with a background in data science to help us create our own virtual assistant. In this internship, you will be part of our data team and play a critical role in shaping how AI is used to support our customers.

• Researching existing RAG strategies and models
• Preprocessing data to tailor the model(s) to specific tasks
• Selecting the most suitable strategies for our business needs
• Developing a working prototype of the RAG model
• Evaluating and optimizing the model's performance