Plant Genomics and Machine Learning Scientist

at  Wild Bioscience

WHO WE ARE:

At Wild Bio we are radically enhancing crops to feed the world sustainably and promote a wilder planet. Wild plants have had half a billion years to evolve natural solutions for thriving in almost every environment on Earth. Our proprietary genetics platform harnesses these wild innovations to enhance the world’s most important crops. Wild-enhanced crops would simultaneously boost farm yields and promote gigaton-scale carbon mitigation strategies. If you’re looking for a start-up that has enormous potential for impact on growers, consumers, and the planet, please read on.
Wild Bio is a well-funded, fast-paced Oxford University spin-out working from state-of-the-art labs and offices at Milton Park, Oxfordshire. We are about to enter an exciting phase of growth and are looking for an experienced, driven, and curious Plant Genomics and Machine Learning Scientist to join us and significantly contribute to delivering the change we believe in.
The role: We’re looking for someone who is excited to work at the intersection of evolutionary biology, machine learning, and plant physiology. The ideal candidate will have previous experience in some combination of comparative genomics, bioinformatics, machine learning, and plant science. Their task will be to help create, curate, and mine deep genomics and plant physiology datasets for insights into creating the world’s highest performing crops.

KNOWLEDGE AND SKILLS:

• An advanced degree (e.g. Ph.D.) in bioinformatics, computational biology, genomics, or a related field where bioinformatics and statistics are applied to large biological datasets.
• Expertise in some combination of comparative genomics, molecular evolution, machine learning, evolutionary biology, and/or plant science.
• Proficiency with machine learning packages in Python and/or R (e.g., Scikit-learn, TensorFlow, PyTorch, Caret).
• Fluency in Python or R, and comfortable working in Linux/Unix.
• Experience working with git and Github.
• Experience working in plant science, or with data from non-model species.
• Excellent communication skills and the ability to work effectively in a multidisciplinary team that includes wet lab scientists.
• Strong problem–solving skills, with an ability to think creatively to meet goals and deadlines.
• Keen to seek out new opportunities to develop, share learnings with others, and strive to support others in their own development and growth.
• Have a curious and courageous mindset, enjoy stepping up to try new things in a changing environment, and taking initiative where there is often ambiguity.
• Challenge established approaches with the aim of improving the system.
• Take initiative where needed with tasks that have not been assigned.

• Build novel comparative genomics pipelines to identify targets for improving crop performance.
• Mine and curate public datasets for useful additions to our machine learning (ML) datasets.
• Collaborate closely with the experimental biology team to guide the generation of new datasets to be integrated into our ML pipelines.
• Leverage your understanding of plant physiology to generate unique insights into plant performance, ensuring a steady stream of ML predictions are prioritised and ready for empirical validation.
• Stay up to date with the latest advancements in the field – e.g. by attending relevant conferences, scouting for new tools and methods, and ensuring a continuous improvement mindset within the computational team.
• Help guide the evolution of the computational infrastructure, including hardware and software resourcing decisions.
• Effectively communicate results, problems, and deliverables to a diverse array of stakeholders.
• Provide bioinformatics expertise to those around you as needed, adopting a coaching and mentoring approach where appropriate.