Bio-ML Scientist (Metabolic Modelling) - Generative Biology Institute

Bio-ML Scientist (Metabolic Modelling) - Generative Biology Institute

EIT - Ellison Institute of Technology

Oxford, United Kingdom

Your Role:

At EIT we are seeking an experienced and detail orientated Bio-ML Scientist to develop AI and machine learning systems that drive GBI’s scientific aims, working alongside researchers and technical staff to address key questions in biological design and discovery. The post-holder will work with multiple data modalities with a focus on biological system modelling and optimisation. This is an exceptional opportunity to join GBI’s Technology Hub on ML Engineering, a fast-growing team at the forefront of AI/ML and synthetic biology with access to exceptional facilities and expertise. We are looking for a colleague who thrives in a team and cares deeply about biological questions, hypotheses, and a biology-centric approach to AI/ML engineering. The role requires expertise in machine learning applied to biological design or discovery, and prior exposure to collaboration with wet lab scientists.

We are particularly interested in candidates with experience in combining AI/ML and genome-scale metabolic models. Our team ethos is based on mutual learning, strong peer-to-peer support, and a deep sense of scientific curiosity and ambition.

Key Responsibilities:

• Research, design and build AI and machine learning systems to address GBI’s research challenges in synthetic biology, genome design, and molecular evolution.
• Lead and contribute to collaborative projects with other MLEng team members, GBI researchers and staff, relevant colleagues across EIT, and external collaborators.
• Work closely with GBI scientists in co-creation of research projects and development of fit-for-purpose computational solutions.
• Provide expert computational biology knowhow to GBI researchers and scope novel avenues of research.
• Interact with the Bioinformatics and Scientific Compute platform teams to support the development of GBI data flows and MLOps.
• Ensure compliance with best practices in ML engineering, including robust and reproducible training pipelines, as well as versioning and documentation of data, models, and code.
• Keep abreast of progress in AIxBio and make use of strategic learning opportunities.
• Lead and contribute to research publications in prestigious venues.
• Organise and prioritise work, operating at the highest standard in the face of multiple competing deadlines.

Requirements:

Essential Knowledge, Skills and Experience:

• PhD degree in a suitable field including, but not limited to, molecular biology, biochemistry, mathematics, computer science, computational biology, engineering, or related discipline.
• Experience in building machine learning models for biological design or discovery tasks, involving processing, visualizing, and analysing various data modalities.
• Ability to abstract high-level biological questions and translate them into actionable computational tasks, evidenced by previous achievements in a comparable industry role, or a promising publication record in scientific journals and technical conferences.
• Ability to learn quickly and dive into a range of problem spaces and computational methods.
• Ability to work and communicate with and within diverse and multidisciplinary teams.
• Fluency in one or more scientific programming languages (Python, R, Julia, etc.) with experience in best practices in machine learning, including documentation.
• Excellent written and oral communication skills for diverse audiences, including colleagues without a computational background.
• Excellent time management skills across competing tasks requiring rapid context switching.

Desirable Knowledge, Skills and Experience:

• Two years of industry or postdoctoral experience in similar roles.
• Proven experience with integration of machine learning methods with genome-scale metabolic models.
• Proven experience with best practices and established software pipelines for genome-scale metabolic modelling, including automated model construction from ‘omics data, flux balance analysis, flux sampling, sensitivity analysis, and related methods in constraint-based modelling.