Machine Learning Scientist — Large multimodal… at Iambic · Boston

Summary: Iambic Therapeutics is a clinical-stage life-science and technology company focused on developing novel medicines through AI-driven discovery technologies. The Machine Learning Scientist will research, develop, and scale multimodal transformer models for drug discovery, collaborating with various teams to ensure model effectiveness in real therapeutic decisions. Responsibilities: - Research and implement architectural improvements to large-scale multimodal transformer models for biomedical applications - Investigate hybrid modeling approaches that combine learned representations with domain-informed structure or inductive biases - Optimize training pipelines for efficiency, stability, and scalability across many-GPU clusters - Develop and apply inference optimization techniques to support deployment in interactive discovery workflows - Design and maintain benchmarking and evaluation frameworks that track model quality across modalities and downstream tasks - Collaborate with ML and software engineering colleagues to deploy and operationalize models - Partner with computational chemists, medicinal chemists, and biologists to ensure model development is grounded in drug discovery needs - Communicate results to internal teams, external partners, and at conferences - Write high-quality research and engineering code: refactor, test, document, and package ML components to support team velocity - Depending on level: Mentor interns and junior team members through technical guidance, code reviews, and best practices in ML experimentation - Contribute to the strategic research roadmap for Enchant and related multimodal technologies Required Qualifications: - MS in ML/CS or a computational STEM field with relevant industry or research experience, or PhD or equivalent industry experience demonstrating comparable depth - Strong Python and PyTorch experience, including implementing and training deep learning models end-to-end - Demonstrated experience training transformer models at scale - Strong engineering habits: reproducible experimentation, clean code, testing, and performance-minded debugging - Comfort working with modern ML infrastructure (e.g., Docker, CUDA, Kubernetes, experiment tracking such as Weights & Biases) Preferred Qualifications: - Experience with multimodal or multi-task model architectures - Training and inference optimization (e.g., mixed precision, kernel optimization, quantization, distributed strategies) - Familiarity with biomedical, chemical, or biological data domains - Distributed training at scale - HPC or large-scale training operations experience Required Skills: Python, PyTorch, Deep learning model training, Transformer models, Reproducible experimentation, Clean code, Testing, Performance debugging, Docker, CUDA, Kubernetes, Experiment tracking, Multimodal model architectures, Training optimization, Inference optimization, Distributed training, Biomedical data domain, engineering habits Benefits: Company paid healthcare, Flexible spending accounts, Voluntary life insurance, 401K matching, Uncapped vacation