Master Thesis Enhancing LLM-Driven SQL Queries for Energy Time Series Analytics

The climate crisis requires a huge transformation in how we produce, consume and distribute our energy. This complex challenge requires new insights based on the enormous amount of data dat is already available. New developments in AI can aid these questions and scape the much needed insights to catalyze data-driven decisions. 

The aim of this thesis is to leverage state-of-the-art AI technologies to enhance data retrieval and analysis in the energy sector. The project will focus on using Large Language Models to generate SQL queries that can answer specific user questions about electricity-related data, such as electricity prices, production, and consumption. The questions may range from historical trends to real-time statistics, and forecasting the future. The required data for this project is already collected and available in our internal database so the focus will be mainly on model development.

Job Description:

We are looking for a highly motivated and talented Master's thesis student in Engineering IT with a specialization in Artificial Intelligence (AI) and Data Science to join our team and work on an exciting research project in the energy sector. This thesis project will involve combining generative AI techniques and Large Language Models (LLMs) to retrieve and analyze time series data with the ultimate goal of facilitating data-driven decision-making and improving our understanding of energy production and consumption. 

Key Tasks and Responsibilities:

1. Literature Review: Conduct an in-depth literature review to understand the current state of AI, generative AI, and LLMs in the context of data retrieval and analysis.

2. Data Preparation: Work with our internal database to access and analyse time series data related to electricity production, consumption, and district heating systems and gain an understanding of the data to be queried.

3. LLM Fine-Tuning: Fine-tune Large Language Models, such as GPT-4 or similar, for generating SQL queries specifically designed for electricity-related questions.

4. SQL Query Generation: Develop algorithms and methodologies for generating SQL queries based on user questions related to electricity data. The queries should be optimized for factual data retrieval.

5. Evaluation and Benchmarking: Create a robust evaluation framework to assess the performance of the generated SQL queries. Compare different LLM-based methods and techniques for their accuracy and efficiency in retrieving factual information.

6. Optimization and Enhancement: Continuously refine and optimize the LLM-based query generation process to improve accuracy. Explore techniques to handle complex queries and edge cases effectively.

7. Thesis Report: Document the research, methodology, results, and findings in a comprehensive Master's thesis report. The report should adhere to academic standards and be suitable for publication.

Qualifications:

- Enrolled in a Master's program in Engineering IT, Computer Science, or a related field with a focus on AI and Data Science.

- Strong programming skills, particularly in Python and SQL.

- Familiarity with Large Language Models and Natural Language Processing (NLP) techniques.

- Knowledge of databases and data manipulation.

- Analytical and problem-solving skills.

- Excellent written and verbal communication skills.

- Ability to work independently and as part of a research team.

Duration:

This Master's thesis position is a temporary role and is expected to last for the duration of your thesis project. The specific duration will be determined based on the requirements of your academic program.

If you are passionate about AI, data science, and the energy sector and are excited about the opportunity to contribute to a project that can make a significant impact in this field, we encourage you to apply. Join us in advancing the frontiers of AI and data-driven decision-making in the energy sector.

About Sigholm

At Sigholm, you have the opportunity to work in an innovative company that wants to make a difference. Our ambition is to change the world for the better by constantly evolving and creating opportunities for each other and our customers. We believe in freedom with responsibility and that together we create an environment where we can learn from each other.