Type: Full-time

Location: Remote (UK/EU based)

Compensation: Competitive (plus equity commensurate with experience)

About us

Bindbridge is pioneering sustainable agriculture through artificial intelligence (AI)-powered molecular glue discovery. With backing from leading venture capitalists including Speedinvest and Nucleus Capital, we are building a computational platform to bring targeted protein degradation to agriculture. Our first goal is to discover herbicides that revolutionise crop protection while minimising environmental impact.

The role

We are looking for an experienced Research Engineer to join our engineering team and help integrate generative AI models into Bindbridge’s molecular glue discovery and design platform.

You will work alongside a team of machine learning (ML) scientists and engineers with experience across Big Tech, startups, and academia. Together, you will take cutting-edge research — implementing state-of-the-art ML papers, extending open-source repositories, and turning prototypes into reliable systems — and make it usable, reproducible, and scalable across our discovery pipeline.

This role combines strong engineering fundamentals with a deep understanding of modern ML workflows, from data preprocessing and experiment tracking to distributed training and large-scale inference. You will take ownership of the experimental infrastructure that accelerates research iteration, enabling our scientists to move rapidly from prototypes to production-ready models and making these models accessible to chemists and biologists.

The ideal candidate has a track record of building robust ML systems, optimising large-scale training pipelines, and bridging the gap between cutting-edge research and deployment.

Key responsibilities

• Implement and productionise ML models — translating research prototypes into robust, maintainable, and tested codebases.
• Design, build, and maintain infrastructure for data ingestion, preprocessing, training, inference, and evaluation.
• Optimise and scale distributed training and inference pipelines across GPUs, clusters, or cloud environments.
• Instrument models and systems with monitoring, logging, and experiment-tracking tools (Weights & Biases, MLflow).
• Collaborate with research scientists to accelerate experiments, validate results, and ensure reproducibility.
• Set software engineering standards, conduct code reviews, share best practices, and contribute to a culture of technical excellence.