Job

• Bachelor’s or Master’s in Computer Science, Electrical Engineering, Data Science, or a related field — or equivalent demonstrable experience.


• Strong Python and hands-on experience with a deep learning framework (PyTorch preferred).


• Solid grasp of ML fundamentals: training and evaluation, overfitting, cross-validation, and how to read a metric honestly (sensitivity, specificity, balanced accuracy, confidence intervals).


• Comfort running and debugging experiments on GPUs, and using experiment-tracking tools (e.g. Weights & Biases).


• Version control with Git as a normal part of your workflow.

We are seeking two AI/ML Research Engineers to expand our experimental capacity across these projects. Reporting to the project leads, the successful candidates will design and execute machine learning models, develop and refine model training pipelines, and ensure that results are rigorous, reproducible, and ready to support publications and patent filings. This is a hands-on research engineering role at the core of the laboratory’s scientific output, with clear opportunities for authorship and professional growth.

Key Responsibilities

• Design and execute experiments. Plan and run machine learning experiments across model architectures, hyperparameters, and random seeds, managing multiple investigations in parallel.


• Develop model pipelines. Implement, refine, and debug training pipelines, including model architectures, loss functions, augmentation strategies, and training procedures.


• Ensure experimental rigor and reproducibility. Follow the laboratory’s experimental protocols and maintain complete experiment records — configurations, code versions, dataset versions — so that all results are fully reproducible.


• Work with clinical datasets. Preprocess, curate, and build data pipelines for complex real-world medical datasets, supporting both internal and external (multi-site) validation.


• Support scientific outputs. Generate the experimental evidence — results, ablations, tables, and figures — underpinning publications and patent filings, contributing as a co-author where appropriate.


• Collaborate across the team. Communicate findings clearly to project leads and clinical stakeholders, and contribute to the laboratory’s shared research knowledge base.


• Document work and methods. Maintain clear documentation of experiments, pipelines, and data-processing steps, and contribute to protocols and technical write-ups that enable others to understand and reproduce the work