The University reviews hundreds of thousands of resumes each year in an imperfect, time consuming manual process. Students on the U-M ITS AI Resume team will create a tool that leverages AI to compare resumes to job postings and sort applications into groups of most likely/less likely good fit candidates.
Abstract:
The University posts thousands of jobs each year each receiving hundreds of job applicants submitting resumes. Reviewing many resumes can be challenging for several reasons:
- Volume Overload: Managing a large number of resumes can be overwhelming. Sorting through hundreds applications is time-consuming and can lead to fatigue.
- Consistency: Ensuring that each resume is evaluated based on the same criteria can be difficult. It’s important to maintain consistency to avoid bias and ensure fairness.
- Skill Matching: Identifying the right skills and qualifications from a diverse range of resumes can be tricky, especially if the resumes are formatted differently or use varied terminology.
- Attention to Detail: It can be easy to overlook important details when scanning through many resumes quickly. Critical information might be missed if not given adequate attention.
- Subjectivity: Personal biases and subjective preferences can influence the evaluation process. It’s crucial to stay objective and base decisions on the qualifications and fit for the role.
- Bias Reduction: Traditional resume reviews can unintentionally perpetuate biases related to gender, race, or background. Implementing a system that reduces bias by focusing on objective criteria can lead to more equitable hiring practices.
The student team will develop a prototype resume sorter to address the highest priority challenges. The tool will take the job description and applicant resumes as input and sort resumes based on criteria selected by the hiring manager. This project expects to use the following techniques:
- Vector embeddings
- Designing vector databases
- Training LLM
- Retrieval-Augmented Generation (RAG)
- Named Entity Recognition
The prototype will be developed using the following tech stack. We don’t expect students to know all parts of the tech stacks, but you must be motivated to build your skills and become proficient. This project will be built on the following tech stack:
- Azure OpenAI API
- Langchain
- Web stack
- Huggingface API
Impact:
Integrating an AI tool to sort, organize, and analyze resumes and cover letters as part of the review process can greatly enhance recruitment efficiency while ensuring objectivity and fairness. By automating initial sorting and enabling advanced querying capabilities, the tool allows HR professionals to quickly identify qualified candidates based on specific experiences. AI also understands the nuances of language, identifying similar or related work experiences, which ensures unbiased and consistent evaluations by removing potential human prejudices. This approach not only saves time but also guarantees that every candidate is assessed against the same criteria, promoting a standardized and equitable selection process.
Scope:
Minimum Viable Product Deliverable (Minimum level of success
-
- Develop an understanding of the current business process, and technical challenges, interview important stakeholders, articulate current failure modes, and develop most relevant use cases.
- Literature review of all relevant techniques and existing technology.
- Demonstrate functional competence in the tech stack by completing a “mini project”. Note – it is unlikely that any student would be fully competent in the entire tech stack before the project. Individual training effort is expected and required
- Develop a strategic approach and project management plan for delivery.
- Complete first prototype and demonstrate functionality of the v1 prototype against applicable system requirements (before the end of Winter term). Develop a strategic plan to address highest priority development in a v2 prototype
Expected Final Deliverable (Expected level of success)
- Complete the v2 prototype and demonstrate the results to the stakeholders.
Stretch Goal Opportunities: (High level of success)
- Include cover letters as additional input.
- Review for techniques that are intended to foul AI reviewers (like adding white text to a resume)
AI Experience (4 Students)
Specific Skills: Broad experience in practical application of AI techniques.
EECS 281 (or equivalent) is required,
EECS 445 (Machine learning) or EECS AI would be a plus.
Likely Majors: CS, DATA, ROB, ECE
General Coding (2 Students)
Specific Skills: General programming skills, good software engineering practice, and design
EECS 281 (or equivalent) is required, experience in full stack development a plus.
Likely Majors: CS, DATA, IOE
Human Systems Development (1 Student)
Specific Skills: Business process mapping, error identification.
EECS 280 (or equivalent) is required.
Likely Majors: CS, IOE, BBA
Additional Desired Skills/Knowledge/Experience
If you have any of these characteristics, highlight them on your Experience and Interest Form and talk about them in your (optional) one way video interview.
- Please include a description of your experience with the different elements in the tech stack in your Experience & Interest Form:
- Practical experience developing web applications, include frontend and backend experience
- Successful team-based project experience
- Excellent interpersonal skills and the willingness to work hard
- Project Management utilizing Agile/Scrum
- Practical experience building generative AI tools.
Mentor
Don Lambert
Director of Emerging Technology and AI Services at ITS.
Don has 28 years of IT experience and has led numerous infrastructure projects. He has a particular interest in process improvement and planning the adoption of new IT services. On the weekends Don enjoys car repair and auto racing.
Weekly Meetings: During the winter 2025 semester, the U-M ITS Resume team will meet on Mondays from 2 – 4 PM in 2166 Duderstadt.
Work Location: The work will take place on the Ann Arbor campus.
Course Substitutions: CE MDE, ChE Elective, CS Capstone/MDE, Data Science MDE/Capstone, EE MDE, CoE Honors, SI Elective/Cognate
Citizenship Requirements: This project is open to all students on campus. International Students: CPT declaration (curricular practical training) is NOT required for this project because the sponsor is part of the University
IP/NDA: Students will sign standard University of Michigan IP/NDA documents.
Summer Project Activities: No summer activity will take place on the project.
Learn more about the expectations for this type of MDP project