Post-Doctoral Researcher

McGill University; Montreal; On-site; CAD 54,000 - 66,000; Full time

Job summary

McGill University in Montreal is inviting a Postdoctoral Fellow in Multimodal Machine Learning to advance a foundation model of human neurotypes by integrating cognitive task performance with conversational text and biometric data. The role focuses on self-supervised representation learning to map diverse signals into a unified latent space.

You will prototype tokenization schemes, work with a psychometrics postdoc to assess cognitive variation vs.

Qualifications

• PhD in machine learning, computer science, computational neuroscience, statistics, or related discipline.
• Proficiency in Python and modern deep learning frameworks.
• Experience with High-performance Computing Infrastructure and GPU clusters.
• Strong research background in multimodal modeling, representation learning, and statistical evaluation of ML models.
• Preferred: Experience with self-supervised learning, NLP, cognitive modeling, privacy-aware methods.

Responsibilities

• Develop tokenization techniques and self-supervised learning methods to integrate diverse data streams (cognitive results, text, psychometrics).
• Train models utilizing novel multi-modal architectures to project qualitative and quantitative data into a unified latent space.
• Collaborate with a psychometrics postdoc to distinguish genuine cognitive variation from measurement error, device effects, and language confounds.
• Design rigorous evaluations focusing on participant-level data separation, model robustness, missing modalities, and generalization.
• Scrutinize models for bias, unsupported sensitive inferences, and stability, ensuring responsible data usage in collaboration with governance bodies.
• Collaborate with software engineers on data preprocessing pipelines and model integration within the game's cloud infrastructure.

Skills

Python

Multimodal modeling

Self-supervised learning

Statistical evaluation

NLP (preferred)

Education

PhD in ML/CS/Neuroscience/Statistics

Tools

HPC infrastructure

GPU clusters

Job description

Please refer to the How to Apply for a Job (for External Candidates) job aid for instructions on how to apply.If you are an active McGill employee (ie: currently in an active contract or position at McGill University), do not apply through this Career Site. Login to your McGill Workday account and apply to this posting using the Find Jobs report (type Find Jobs in the search bar).Postdoctoral Fellow, Multimodal Machine LearningRole OverviewThe Postdoctoral Fellow will develop techniques to build a foundation model of human neurotypes by integrating cognitive task performance, conversational text, and biometric data. The core challenge is utilizing self-supervised representation learning to construct a continuous latent manifold of individual differences.Responsibilities Develop tokenization techniques and self-supervised learning methods to integrate diverse data streams (cognitive results, text, creative choices, psychometrics). Train models utilizing novel multi-modal architectures to project qualitative and quantitative data into a unified latent space. Work closely with a psychometrics postdoc to distinguish genuine cognitive variation from measurement error, device effects, and language confounds. Design rigorous evaluations focusing on participant-level data separation, model robustness, missing modalities, and generalization. Scrutinize models for bias, unsupported sensitive inferences, and stability, ensuring responsible data usage in collaboration with governance bodies. Collaborate with software engineers on data preprocessing pipelines and model integration within the game's cloud infrastructure.Qualifications PhD in machine learning, computer science, computational neuroscience, statistics, or a related discipline. Proficiency in Python and modern deep learning frameworks. Experience with High-performance Computing Infrastructure and GPU clusters. Strong research background in multimodal modeling, representation learning, and statistical evaluation of machine learning models. Preferred: Experience with self-supervised learning, natural language processing (NLP), cognitive modeling, and privacy-aware methods.This position is covered by the AMURE collective agreement: https://www.mcgill.ca/hr/employee-relations/assocs-unionsBefore applying, please note that to work at McGill University, you must be both authorized to work in Canada and willing to work in the province of Quebec at the campus where the position is based / located.McGill University is an English-language university where most teaching and research activities are conducted in the English language, thereby requiring English communication both verbally and in writing.Annual Salary:$60,000.00Hours per Week:35 (Full time)Location:Montreal Neuro.Supervisor:Associate ProfessorPosition Start Date:2027-01-01Position End Date:2027-12-31Deadline to Apply:2026-11-13McGill University hires on the basis of merit and is strongly committed to equity and diversity within its community. We welcome applications from racialized persons/visible minorities, women, Indigenous persons, persons with disabilities, ethnic minorities, and persons of minority sexual orientations and gender identities, as well as from all qualified candidates with the skills and knowledge to productively engage with diverse communities. McGill implements an employment equity program and encourages members of designated groups to self-identify. Persons with disabilities who anticipate needing accommodations for any part of the application process may contact, in confidence, [e-mail] .