Description

You will design, train, and evaluate transformer models to support next-generation AI for genomics.

This role is remote.

Responsibilities

• Refactor the AI codebase to support new features and training or inference contexts.
• Redesign neural network architectures to incorporate new sequencing datatypes.
• Collaborate with genomics experts to define and pre-process training and validation datasets.
• Execute training runs on multiple sequencing datasets.
• Work with Machine Learning Engineers to deploy trained models at scale.

Required Skills

• 5+ years of experience in data science or related roles.
• Proficiency with Python and PyTorch.
• Experience with Docker and Kubernetes.
• Hands-on use of Jupyter.
• Expertise in Deep Learning and Transformers (e.g., BERT and derivatives).
• Experience with Natural Language Processing (NLP) and Large Language Models (LLMs).
• Bachelor's degree or equivalent experience.

Preferred Skills

• Experience working with genomics data or molecular genetics.
• Knowledge of distributed computing tools such as Ray, Dask, or Spark.

Key Skills

Education

Any Graduate