Research Engineer in EEG-Based Detection of Concealed Knowledge Full-time NEW

Research Engineer in EEG-Based Detection of Concealed Knowledge

Lund University was founded in 1666 and is repeatedly ranked among the world's top universities. The University has around 46,000 students and 8,500 staff based in Lund, Helsingborg, and Malmö. We are united in our efforts to understand, explain, and improve our world and the human condition.

The position is based at the Department of Psychology at Lund University, within a research environment focused on the cognitive neuroscience of memory. The group combines high-temporal-resolution electrophysiology (EEG), eye tracking, and advanced computational approaches to investigate how information is encoded, integrated, and retrieved from memory.

The successful candidate will contribute to a project investigating the neural detection of concealed knowledge using EEG and advanced machine-learning approaches. The project focuses on identifying neural signatures of recognition and memory retrieval at the single-trial level, with particular emphasis on time-resolved decoding and generalization of cognitive states.

A central component of the project is the development of real-time or near-real-time EEG decoding approaches, in which classification models are trained and updated during ongoing data acquisition. This involves designing pipelines that integrate preprocessing, feature extraction, and model training under temporal constraints, while ensuring robustness, generalizability, and interpretability.

The main duties include:

• Designing, implementing, and analyzing EEG experiments related to memory and concealed knowledge detection
• Developing and critically evaluating machine learning pipelines for single-trial EEG decoding
• Analyzing time-resolved neural data (e.g., temporal generalization, cross-condition decoding)
• Implementing advanced preprocessing pipelines (artifact correction, ICA, etc.)
• Contributing to the development of real-time or near real-time decoding pipelines, including online preprocessing, feature extraction, and model updating
• Evaluating trade-offs between latency, accuracy, and generalization in online classification settings
• Conducting statistically rigorous analyses (e.g., permutation testing, mixed-effects modeling)

We are seeking a candidate with a PhD in Psychology who demonstrates advanced methodological expertise in EEG analysis and machine learning. The candidate should have a strong track record of applying and critically evaluating classification or decoding approaches to neural or time-series data, including single-trial analyses and rigorous model validation.

The ideal candidate combines solid knowledge of electrophysiological signal processing with strong programming skills (Python and/or MATLAB; e.g., MNE-Python, scikit-learn, FieldTrip, EEGLAB) and statistical competence appropriate for neuroimaging data. Experience moving beyond standard ERP-based analyses toward multivariate, time-resolved approaches is expected.

Particular value will be placed on experience with time-resolved EEG decoding (e.g., temporal generalization), as well as a principled understanding of feature construction, dimensionality reduction, and model interpretability for neural data. Familiarity with multivariate frameworks (e.g., MVPA, RSA) and/or modern approaches to time-series modeling (including deep learning, where appropriate) is advantageous. Experience with real-time data processing, online classification, or low-latency machine-learning pipelines is highly advantageous, as is experience developing reproducible, well-documented analysis workflows.

Candidates must demonstrate the ability to conduct independent research at a high level, as evidenced by relevant peer-reviewed publications.

Assessment criteria:

• Depth of methodological expertise in EEG and neural data modeling
• Demonstrated ability to develop and evaluate decoding/classification approaches
• Scientific quality, originality, and relevance of previous research
• Ability to work independently and contribute to a collaborative research environment

Scope: 20% over 6 months