Machine Learning Engineer, Computational Biology

Responsibilities

• Lead the engineering components of long-term research projects encompassing all stages of the project lifecycle. Responsibilities include data generation pipelines, database management, development and maintenance of codebases, as well as the design and execution of analysis pipelines and reporting mechanisms.
• Collaborate closely with the Core ML and Engineering teams to integrate and optimise cutting-edge methodologies for the distribution and scaling of large-scale (billion parameter plus) ML models.
• Align with engineering leads across other critical projects to improve standardisation and methodological best practices across the company.
• Develop and maintain robust, high-quality software solutions. Ensure code is modular, well-documented, and integrates smoothly with continuous integration systems. Work in collaboration with Research Scientists, Engineers, and technical leads from various projects to uphold high coding standards and foster standardisation and methodological best practices across the Research Team.
• Deploy machine learning models and associated processes across large-scale, distributed computing infrastructures, including CPUs, GPUs, and TPUs, utilising both in-house and cloud-based platforms.
• Manage the efficient, reproducible, and performant handling of complex, multi-modal biological data. This includes optimising data generation, storage, and retrieval processes, particularly through advanced database management systems like SQL.
• Actively contribute to the team's research initiatives, including publishing results and participating in open-source projects.
• Report and present experimental results and research findings clearly and effectively, both internally and externally, verbally and in writing.

Requirements

• Masters-level degree in Computational Science, Machine Learning or a related scientific field.
• Experience using Deep Learning frameworks like PyTorch, Tensorflow and/or Jax.
• Strong software engineering experience (Object-Oriented Programming, Unit Testing, Profiling, CI, Docker) via previous work or contributions to open-source projects.
• Excellent communication skills and collaborative spirit.

Desirables

• Experience in professional research teams; either industrial or through PhD/post-doctoral positions.
• Experience with computational biology and biological data curation and management.
• Experience applying computational modelling techniques such as sequence alignment, protein structure prediction and inverse folding, molecular dynamics simulations, and quantum chemistry calculations with density functional theory, and more.
• Published scientific papers in related domains such as ML or bioinformatics.