博士后研究员

Zhongguancun Academy; California; On-site; USD 45,000 - 75,000; Full time

Job summary

Beijing Zhongguancun Academy seeks 1–3 postdoctoral researchers to advance AI for Science in protein sequence-structure-function modeling and mutation effect prediction. You will develop next-generation AI methods, collaborate with experimental teams, and contribute to open benchmarks and datasets.

The role emphasizes independent research, reproducible workflows, and publication quality. Applicants with PhD within the last three years, strong Python/PyTorch skills, and a track record of

Qualifications

• PhD degree or near completion with strong life science/AI background.
• PhD awarded within the last 3 years is preferred.
• Proficiency in Python and PyTorch; experience with Linux, GPU computing, and reproducible research workflows.
• Excellent English writing and communication; first-author publications or high-quality open-source work are a plus.

Responsibilities

• Conduct independent research in AI for Science and biological foundation models.
• Develop and evaluate protein sequence-structure-function models and mutation-effect predictors.
• Collaborate with experimental teams to validate predictions and support protein engineering efforts.
• Publish high-quality papers and contribute to grant and project applications; mentor students.

Skills

First-author publications

English paper writing

Independent research

Interdisciplinary collaboration

Education

PhD degree

Tools

Python

PyTorch

Linux

Git

GPU

Job description

Background：To meet the needs of scientific research development, the Department of Intelligent Science and Technology at Beijing Zhongguancun Academy is recruiting 1–3 postdoctoral researchers from around the world. Our team focuses on AI for Science, biological foundation models, protein sequence-structure-function modeling, mutation effect prediction, and AI-driven protein engineering. We aim to develop next-generation AI methods to address real-world biological challenges and advance their applications in protein function analysis, optimization of enzymes/antibodies/antigens, interpretation of disease variants, and biological design. We welcome outstanding young scholars with backgrounds in artificial intelligence, computer science, bioinformatics, computational biology, structural biology, protein engineering, statistics, applied mathematics, and related fields to apply.

The postdoctoral researchers will focus on AI for Science and biological foundation models, including protein sequence-structure-function modeling, mutation effect prediction, and AI-driven protein engineering, developing next-generation AI methods for real-world biological problems and promoting their applications in protein function analysis, optimization of enzymes/antibodies/antigens, interpretation of disease variants, and biological design.

1. Research Directions

• Foundation Models for Proteins and Biological Sequences: Protein language models, multimodal models, generative models, structure-aware models, retrieval-augmented methods, and efficient fine-tuning techniques.
• Mutation Effect Prediction and Variant Interpretation: Predicting the impact of mutations on stability, expression, activity, binding, antigenicity, drug resistance, or pathogenicity, with a focus on few-shot learning, generalization, uncertainty quantification, and interpretability.
• Model-Experiment Closed Loop and Protein Engineering Applications: Integrating DMS/MAVE, high-throughput sequencing, structural data, and public databases to support tasks such as mutant library design, functional validation, and optimization of enzymes/antibodies/antigens.
• Toolchains and Open Benchmarks for Biological Foundation Models: Developing datasets, evaluation systems, model services, benchmarks, pipelines, and open-source software platforms.

2. Job Responsibilities

• Conduct independent research in the above directions, building and evaluating foundation models for proteins/biological sequences and mutation effect prediction models.
• Integrate public and team data to establish reproducible data processing, training, and evaluation workflows.
• Collaborate with experimental teams to advance model predictions into functional validation or protein engineering experiments.
• Publish high-quality papers, participate in grant and project applications, and assist with team research collaboration and student mentorship.

3. Qualifications

• Have obtained or be about to obtain a Ph.D. degree, generally under 35 years of age, and have received the doctoral degree generally no more than 3 years ago, capable of working full-time at the station.
• Have a background in artificial intelligence, machine learning, bioinformatics, computational biology, structural biology, protein engineering, statistics, or related fields.
• Proficient in Python and PyTorch, with experience in Linux, GPU, Git, and reproducible research workflows.
• Have a genuine interest in life science problems and the ability to understand protein sequences, structures, evolution, functional experimental data, or biomedical data.
• Possess independent research ability and English paper writing skills, with first-author or major-author publications in high-level journals, or high-quality open-source projects, models, or datasets.
• Have good communication skills and a willingness for interdisciplinary collaboration.
• Background in artificial intelligence, machine learning, bioinformatics, computational biology, structural biology, protein engineering, statistics, or related fields.
• Proficient in Python and PyTorch, with experience in Linux, GPU, Git, and reproducible research workflows.
• Ability to understand protein sequences, structures, evolution, functional experimental data, or biomedical data.
• Independent research ability and English paper writing skills.