for Teaching Assistants, Graduates Service Assistants & Sessional Lecturers

TA - Winter 2027-CIS*6670 Special Topics in Cybersecurity: AI and LLM Security and Privacy

Teaching Assistant Work Assignment

Type of Work Assignment and Bargaining Unit:

GTA, Unit 1

Academic Unit:

School of Computer Science

Semester(s) of Assignment(s):

Winter 2027

This Work Assignment(s) may be assigned to fulfill the terms and conditions of a guaranteed Job Security Period:

N/A

Course Number:

CIS*6670

Course Name:

Special Topics in Cybersecurity: AI and LLM Security and Privacy

Course Format:

In-Class

Course Description:

See Course Calendar

Other Course Description or Assignment Information:

The total number of assignments is a low estimate of the number of available appointments. The final number may be higher and it will depend on class enrollment at the time of assignment.

60

Level of Appointment for GTA, GSA-1 UTA(s)

The following is an estimate of number and levels of available appointments at the time of posting. This may change (increase or decrease) at the time of assignment contingent on departmental needs.

This Posting includes Multiple Work Assignments:

No

Number of Available 0.25 (35 hour) Work Assignments:

0

Number of Available 0.5 (70 hour) Work Assignments:

0

Number of Available 0.75 (105 hour) Work Assignments:

0

Number of Available Full 1.0 (140 hour) Work Assignments:

1

Total Number (Load) of Assignment(s) Available

1

Duties and Responsibilities

Anticipated Duties and Responsibilities:

- Orientation-Training
- Office Hours
- Preparation
- Student Consultation
- Meetings
- Invigilating Exams
- Grading

Qualifications

Required Qualifications:

- As per the Collective Agreement, must be enrolled as a student in the Winter 2027 semester;
- Practical experience with machine learning in Python,



including PyTorch, Hugging Face (Transformers, Datasets) and Jupyter notebooks;
- Familiarity with adversarial machine learning and LLM security concepts, including evasion and poisoning attacks, membership inference, jailbreaking, and direct and indirect prompt injectio;
- Hands-on experience running and evaluating open-weight large language models locally (e.g., Ollama, vLLM), including working on GPU-equipped Linux machines;
- Familiarity with retrieval-augmented generation (RAG) pipelines and LLM agents that use tools (e.g., vector databases, LangChain or similar frameworks);
- Familiarity with the Linux command line, Python virtual environments and basic shell scripting;
- Robust communication skills and the ability to clearly explain technical concepts to students both verbally and in writing, with patience for those new to machine learning.

Preferred Qualifications:

- Experience with LLM red-teaming and evaluation tools (e.g., garak, PyRIT, AgentDojo, HarmBench);
- Experience with privacy-preserving machine learning, including differential privacy and DP-SGD (e.g., Opacus), or federated learning;
- Research experience or graduate coursework in AI/ML security, privacy or trustworthy AI, including reading and critiquing research papers;
- Ability to give feedback on student research projects and writing in a conference paper format (e.g., LaTeX, IEEE/ACM templates).

Days Required and Wages

Days and Times Required:

See duties and qualifications above,



as well as WebAdvisor for lecture and lab days and times. Dates and times will be reviewed with the instructor during the first week of the course.Must be able to facilitate labs.

Period of the Work Assignment (Start Date and End Date):

January 7, 2027 to May 7, 2027

Wage Rate (per hour, per semester, per Full-load 1.0 Work Assignment):

Other Posting Information

Application Deadline (All postings will automatically expire at 11:59 pm on this day):

Thursday, November 12, 2026

Posting Email Contact:

Hiring Contact Information:

Christine Harris, Instructional Support Coordinator -

At the University of Guelph, fostering a culture of inclusion is an institutional imperative. The University invites and encourages applications from all qualified individuals, including from groups that are traditionally underrepresented in employment, who may contribute to further diversification of our Institution. For more information, the Office of Diversity and Human Rights (DHR) is a welcoming, safe and confidential one-stop shop for information, training and support on issues relating to diversity and human rights on our campus.

All applicants must be eligible to work in Canada specifically at the University of Guelph before applying for an academic work assignment. All successful applicants must perform their work in Ontario and must be able to attend on-campus in-person meetings as required.

Teaching Assistant work assignments are unionized with CUPE 3913 and their terms and conditions of work are covered by the Unit 1 Collective Agreement between the University and CUPE 3913 (email contact: ).

The use of AI to perform job responsibilities must be directed by or approved beforehand in writing by the supervisor or course instructor.

#J-18808-Ljbffr

📌 Special Topics in Cybersecurity: AI and LLM Security and Privacy (Guelph)
🏢 University of Guelph
📍 Guelph