Postdoctoral Appointee – Computational Biology and Generative AI
| Company | Argonne National Laboratory |
|---|---|
| Location | Woodridge, IL, USA |
| Salary | $70758 – $110379.55 |
| Type | Full-Time |
| Degrees | PhD |
| Experience Level | Junior, Mid Level |
Requirements
- Recent or soon-to-be completed Ph.D. within the last 5 years in Computational Biology, Bioinformatics, Machine Learning, Artificial Intelligence, Virology, or a related field
- Strong programming skills in Python, R, or Julia, with experience in deep learning frameworks (TensorFlow/PyTorch)
- Experience with large-scale genomic/proteomic datasets and machine learning applied to biological sequences
- Knowledge of phylogenetics, protein structure-function analysis, and viral evolution
- Familiarity with deep mutational scanning datasets and methods for quantifying viral immune escape
- Strong publication record in relevant fields
- Ability to work independently and collaboratively in a multidisciplinary research environment
- Ability to model Argonne’s core values of impact, safety, integrity, safety and teamwork
Responsibilities
- Develop and refine generative AI models for predicting viral evolution, including SARS-CoV-2 and influenza A/H3N2
- Integrate deep mutational scanning data to assess viral fitness and immune escape, collaborating with experimental virologists
- Work with large-scale genomic and proteomic datasets from BV-BRC, GISAID, and other sources to train and validate AI models
- Develop computational workflows incorporating LLMs, Monte Carlo Tree Search (MCTS), phylogenetic inference, uncertainty quantification, and epidemiological modeling
- Perform predictive modeling using high-performance computing (HPC) infrastructure
- Validate computational predictions by collaborating with experimental groups conducting reverse genetics studies and structural biology analyses
- Publish findings in high-impact journals and present research at leading conferences
Preferred Qualifications
- Experience with generative models (transformers, diffusion models, VAEs, GANs) applied to biological sequences
- Familiarity with the theory behind modern molecular biology techniques
- Knowledge of HPC environments, cloud computing, or GPU-accelerated machine learning
- Background in Monte Carlo Tree Search (MCTS) or reinforcement learning for sequence generation
- Familiarity with biological sequence alignment tools (MAFFT, FastTree, RAxML-NG)
- Experience with protein structure modeling (AlphaFold, Rosetta, ESMFold)