SeniorAIAlgorithmEngineer(Bio-genetics/SyntheticBiology)

**Job Description:** **Responsibilities:** Lead the architecture design, pre-training, and fine-tuning of vertical Large Language Models (LLMs) for the bio-genetics sector (e.g., gene interpretation, breeding decision models), enhancing inference and generation capabilities in specific biological scenarios. * Spearhead the cleaning, standardization, and feature engineering of multimodal biological data (genomics, transcriptomics, clinical phenotypes, etc.) to construct high-quality instruction-tuning datasets and knowledge bases. * Develop automated decision-making systems based on Multi-Agent frameworks, achieving an end-to-end closed loop from natural language instructions to experimental protocol generation and equipment scheduling. * Explore the application of cutting-edge AI technologies (such as Chain-of-Thought, Reinforcement Learning, and Knowledge Graphs) in precision medicine and smart breeding to address long-tail problems in traditional bioinformatics analysis. * Collaborate closely with biologists and clinicians to translate complex biological problems into computable algorithmic models, driving the deployment and iteration of algorithms in production environments. **Requirements** * Master’s degree or higher in Computer Science, Bioinformatics, Artificial Intelligence, or related fields, with 3+ years of algorithm development experience. * Proficient in Python programming and deep learning frameworks like PyTorch or TensorFlow, with a solid foundation in Transformer architecture and NLP algorithms. * Hands-on experience in fine-tuning Large Language Models (LLMs); familiar with RLHF, Prompt Engineering, etc. Experience in developing models for the bio/medical vertical is highly preferred. * Experience in Multi-Agent systems or Knowledge Graph development, capable of handling complex logical reasoning and task planning. * Familiar with basic bioinformatics workflows (e.g., GATK, sequence alignment) and fundamental principles of genomics; possesses stron