ByteDance is looking to solve the problem of researching cutting-edge posttrain technologies and providing core posttrain capabilities for unified multimodal large models, specifically in the area of RNA design using LLMs and fine-tuned generative models.
Requirements
- Research experience in sequence modeling, generative models, or scientific ML.
- Publications in top ML or computational biology venues (e.g., NeurIPS, RECOMB, ISMB).
- Strong coding skills in Python and familiarity with deep learning libraries.
- Experience with RNA design tools (e.g., ViennaRNA, Eterna, EternaFold).
- Knowledge of constraint-guided generation, structure prediction, or energy-based modeling.
- Background in applying ML to biological systems or physical simulations.
Responsibilities
- Develop methods for RNA design using LLMs and fine-tuned generative models.
- Incorporate reward signals or constraints based on molecular structure, energy, or biological properties.
- Design and benchmark models using RNA datasets and structure simulators.
- Collaborate with interdisciplinary teams to bring LLM capabilities to real-world scientific applications.
Other
- Currently pursuing a PhD in Computer Science, Computational Biology, Bioinformatics, or a related area.
- Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment
- Qualified applicants with arrest or conviction records will be considered for employment in accordance with all federal, state, and local laws
- 10 paid holidays per year and paid sick time (56 hours if hired in first half of year, 40 if hired in second half of year)
