AI for Astrophysics Research Technician

University of Chicago•Hyde Park, IL

6d•Onsite

About The Position

This position supports a research project at the intersection of astrophysics, cosmology, and artificial intelligence / machine learning (AI/ML), focused on strong gravitational lensing analysis using simulation-based inference (SBI) with domain adaptation techniques. The work centers on developing robust, transferable inference pipelines that bridge the gap between synthetic simulations and real observational data from large-scale astronomical surveys such as DES and LSST. The research technician will contribute to the design and implementation of deep learning methods aimed at addressing fundamental questions in cosmology, working with large datasets and modern AI/ML inference methods throughout the project.

Requirements

Minimum requirements include vocational training, apprenticeships or the equivalent experience in related field (not typically required to have a four-year degree).
Minimum requirements include knowledge and skills developed through 2-5 years of work experience in a related job discipline.
Computer programming, particularly Python.
Excellent written and oral communication skills.
Ability to work in a diverse group that includes students, postdocs, and senior scientists.
Ability to juggle multiple tasks.

Nice To Haves

BSc or MSc degree in astrophysics, physics, computer science or related discipline.
Python programming for scientific applications.
Experience with AI/ML algorithms.

Responsibilities

Develop and benchmark simulation-based inference algorithms (e.g., NPE) for strong gravitational lensing parameter estimation.
Implement domain adaptation techniques to improve model robustness and transferability between simulated and real survey data.
Generate and curate strong lensing simulations using tools such as lenstronomy or similar ray-tracing frameworks.
Train and evaluate deep learning models on simulated datasets and validate performance on realistic or real observational data.
Investigate and mitigate systematic biases arising from simulation-to-reality mismatches (sim-to-real gap).
Collaborate with team members to integrate inference pipelines into end-to-end analysis workflows.
Conduct literature reviews to stay current with advances in SBI, domain adaptation, and strong lensing science.
Document code, experiments, and results clearly, maintaining reproducible research practices.
Present progress regularly in team meetings and contribute to scientific publications or conference proceedings.
Provides technical and administrative support for a research project.
Collects and enters data.
Assists in analyzing data.
Assists with preparation of reports, manuscripts and other documents.
Performs other related work as needed.