ML Research Engineer, London

The role

Research Engineers will develop and optimize state-of-the-art AI models to advance foundational models for drug design. They will partner with scientists and engineers to implement research concepts and build robust data pipelines and infrastructure.

What you will do

• Translate research concepts into practical implementations
• Develop and optimize state-of-the-art AI models
• Build and maintain robust codebases, data pipelines, and infrastructure
• Design, implement, and run experiments to evaluate ML model performance
• Evaluate, tune, and maintain AI/ML models
• Implement algorithms and software to analyze AI model performance
• Optimize performance of AI/ML models such as Diffusion models, Transformers, and GNNs
• Advise on bringing AI/ML models to production and integrating them into products
• Develop specialized tools, frameworks, and infrastructure
• Collaborate with research scientists and engineers through discussions and code reviews

Required qualifications

• 4+ years of experience working in reputable tech companies or research labs
• Advanced degree (Master’s or PhD) in a highly quantitative field (Computer Science, AI, Physics, Mathematics, etc.) or equivalent practical experience
• Deep understanding of machine learning principles and techniques
• Strong proficiency in deep learning frameworks such as JAX or PyTorch
• Hands-on experience building and working with modern model architectures (e.g., Transformers, GNNs, Diffusion Models)
• Experience taking models from conception to production (scoping, data analysis, training, debugging, evaluation, benchmarking, and deployment)
• Excellent software development skills with strong algorithms and data structures fundamentals
• Strong written and verbal communication skills
• Ability to navigate ambiguity, propose and own complex projects, and adapt to new domains

Nice to have

• History of scientific contributions (e.g., publications at NeurIPS, ICML, ICLR, CVPR) or significant contributions to state-of-the-art AI models
• Experience training models across distributed systems (multi-GPU/multi-node)
• Optimizing training and inference performance (e.g., XLA, Triton, CUDA, Pallas)
• Strong interest in, or knowledge of, biochemistry, computational biology, or drug discovery fundamentals
• Experience developing models developed for real-world applications
• Solid technical infrastructure knowledge and experience with low-level engineering (e.g., GCP, Kubernetes, Docker)

About the company

Isomorphic Labs (IsoLabs) was launched in 2021 to advance human health by building on and beyond the Nobel-winning AlphaFold system. The company uses AI to model complex biological phenomena to help design novel molecules and develop innovative medicines.