Duration: 3 or 6 months, depending on the applicant’s preference

Overview:

PatentAssist.ai is at the forefront of leveraging advanced AI and machine learning technologies to revolutionize patent analysis and management. We are looking for a passionate and skilled Data Engineer Intern to join our team in developing a cutting-edge patent database utilizing vector embedding technologies. This project involves data scraping, refining, denoising, and organizing vast amounts of patent information into a highly efficient and searchable vector embedding database.

Responsibilities:

Collaborate with the development team to design and implement a vector embedding database tailored for patent data.
Employ data scraping techniques to gather patent information from various sources.
Refine and preprocess data to enhance quality and relevancy, including denoising and organizing data effectively.
Utilize embedding models to convert patent documents into high-dimensional vector spaces, facilitating efficient storage and retrieval.
Implement indexing and search algorithms to support similarity searches within the patent database, enabling advanced query capabilities.
Monitor and optimize the performance of the database, ensuring high efficiency and accuracy in data handling.
Document the development process, including challenges faced and solutions implemented, contributing to the project’s knowledge base.

Requirements:

Currently pursuing a Bachelor’s or Master’s degree in Computer Science, Data Science, or a related field.
Strong foundation in database management systems (SQL, NoSQL, MangoDB, with a keen interest in vector databases and AI applications).
Proficiency in programming languages such as Python, along with experience in data scraping and preprocessing techniques.
Familiarity with machine learning models, particularly in the context of creating and managing vector embeddings (using LLM , OpenAI, miniLM).
Optional: Some knowledge about Elastic search infrastructure.
Excellent problem-solving skills and the ability to work independently on complex tasks.
Strong communication skills, capable of collaborating effectively with a remote team.

Benefits:

Valuable hands-on experience in a cutting-edge field at the intersection of AI, machine learning, and patent management.
Internship and work experience certificate upon successful completion of the project.
Competitive salary, negotiable based on skill level and performance.
Opportunity for an endorsement certificate from PatentAssist.ai for outstanding contributions to the project.

Application Process:

Interested candidates should submit their resume on [email protected] along with a cover letter highlighting their experience and interest in vector, SQL and NoSQL databases and AI technologies. Please specify your availability for the 3 or 6-month internship duration.