Job Description
About the Role:
We are seeking a highly motivated AI Intern to assist in collecting and distilling structured knowledge from physics textbooks and research materials using Large Language Models (LLMs). You will work with state-of-the-art generative AI tools including OpenAI GPT-4o, DeepSeek, and custom Python pipelines to extract, organize, and refine scientific content.
This internship is ideal for students or recent graduates with interests in physics, machine learning, and natural language processing (NLP). You’ll gain hands-on experience with LLMs and AI development workflows.
Requirements:
- Strong programming skills in Python, including libraries.
- Basic understanding of physics topics (high school to undergraduate level).
- Familiarity with LLMs and tools such as OpenAI API, DeepSeek, or HuggingFace models.
- Experience with prompt engineering, text preprocessing, and data annotation.
- Knowledge of data wrangling and working with unstructured text.
- Good problem-solving skills and the ability to work independently and collaboratively.
Responsibilities
Key Responsibilities:
- Scrape, clean, and structure content from publicly available physics textbooks and scientific resources.
- Build Python scripts to preprocess and segment content into prompt-ready formats for LLMs.
- Design and run distillation pipelines to convert textbook content into concise explanations, Q&A pairs, and concept summaries.
- Leverage generative models (e.g., GPT-4o, DeepSeek) for summarization, question generation, and conceptual clarification.
- Evaluate and iterate on model outputs for clarity, factuality, and completeness.
Benefits
Great Team To Start Your Career.
Possibility of permenant position after the internship.
Fair Compensation.
At ComplyMarket, we value diversity and believe that a range of backgrounds and perspectives enhances our ability to serve our customers. We are an equal opportunity employer and welcome applications from all qualified candidates.
fi
