Machine Learning Scientist — Large Multimodal Models

Iambic Iambic · Pharma · Boston, MA · Technology

Seeking a Machine Learning Scientist to research, develop, and scale a multimodal transformer model for drug discovery. The role involves architecture research, hybrid modeling, training/inference optimization, and deployment in interactive workflows.

What you'd actually do

  1. Research and implement architectural improvements to large-scale multimodal transformer models for biomedical applications
  2. Investigate hybrid modeling approaches that combine learned representations with domain-informed structure or inductive biases
  3. Optimize training pipelines for efficiency, stability, and scalability across many-GPU clusters
  4. Develop and apply inference optimization techniques to support deployment in interactive discovery workflows
  5. Design and maintain benchmarking and evaluation frameworks that track model quality across modalities and downstream tasks

Skills

Required

  • Python
  • PyTorch
  • implementing and training deep learning models end-to-end
  • training transformer models at scale
  • reproducible experimentation
  • clean code
  • testing
  • performance-minded debugging
  • Docker
  • CUDA
  • Kubernetes
  • experiment tracking

Nice to have

  • multimodal or multi-task model architectures
  • training and inference optimization
  • biomedical, chemical, or biological data domains
  • distributed training at scale
  • HPC or large-scale training operations experience

What the JD emphasized

  • multimodal transformer models
  • training transformer models at scale
  • multimodal or multi-task model architectures
  • distributed training at scale

Other signals

  • multimodal transformer model
  • drug discovery
  • large-scale foundation models