As an AI Engineer at HHMI’s Janelia Research Campus, you will join the AI+CryoET project to develop advanced machine learning methods for 3D particle detection and structural analysis in cryo-electron tomography data. Your daily tasks include creating deep learning models to detect gold nanoparticles and macromolecular particles like nucleosomes, improving tomogram reconstructions through innovative alignment techniques, and designing robust training pipelines that handle complex imaging challenges. You will collaborate closely with experimentalists and computational scientists across multiple institutions to ensure your AI models are effective in real-world scenarios. This role requires expertise in Python, PyTorch or JAX, experience with 3D image analysis, and familiarity with GPU-based computing environments and cryoET datasets. Ideal candidates have a background in computer science, applied mathematics, physics, or computational chemistry, along with a track record of open-source contributions and interdisciplinary collaboration.
Skills
Python
PyTorch
JAX
GPU-based computing environments
Linux HPC clusters
Molecular dynamics simulations
OpenMM
LAMMPS
CryoET software tools
IMOD
Warp
RELION
AreTomo
3D image analysis
Deep learning models
CI/CD
What you'll do
Develop deep learning models to detect and localize gold nanoparticles and macromolecular particles in cryoET data.
Improve tomogram reconstruction by leveraging gold nanoparticle detections, addressing challenges like tilt-series alignment and low signal-to-noise conditions.
Design and execute AI model training pipelines that handle missing wedge artifacts and CTF effects from MD-derived synthetic training data.
Identify areas for additional human annotation to enhance the accuracy of particle detection and structural analysis in cryoET datasets.
Contribute to scientific publications and present findings at conferences, ensuring results are reproducible through well-documented codebases.
What we're looking for
Master's or PhD in Computer Science, Applied Mathematics, Physics, Computational Chemistry, or related field.
3+ years experience training and evaluating deep learning models on 3D image data.
Strong Python skills with proficiency in PyTorch and/or JAX.
Experience with scalable GPU-based computing environments and high-throughput processing for large-scale data.
Familiarity with cryo-EM/ET data processing, tomographic reconstruction, or related inverse problems.
Commitment to open science and excellent communication skills for interdisciplinary collaboration.
Rigorous experimental design capabilities including model comparisons and reproducibility.
Market check
Salary context
This listing doesn't show a salary. Similar roles on FindRole typically pay
$152,000–$241,500.
Peer median band
$152,000–$241,500
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$161,125–$246,150
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
Employer
About Howard Hughes Medical Institute (HHMI)
Howard Hughes Medical Institute (HHMI) is one of the largest private biomedical research organizations in the world, funding basic research and science education to advance human health and knowledge. Industry: Biomedical Research & Science Education
Howard Hughes Medical Institute (HHMI) currently has
4 open roles
on FindRole.