AI Scientist (Protein foundation models)

At OpenProtein.AI, we are decoding the fundamental language of proteins to transform biological discovery and design. Our cloud-based SaaS platform enables biologists, bioinformaticians, and ML engineers across leading pharmaceutical companies, biotechs, and innovative startups to predict variant effects, optimize protein function, design novel proteins de novo, and accelerate design-build-test cycles with unprecedented data efficiency. We are building the next generation of protein foundation models, harnessing billions of years of evolution to break conventional scaling laws and deliver 20x superior design outcomes and 3x higher success rates with as few as tens of training examples. Join us in building the future of AIxBiology.

• Develop deep learning and other algorithmic solutions for problems in protein structure prediction, sequence generation, function prediction, and other biomolecular areas
• Carry out research projects from ideation to experiment planning and execution to presentation and deployment of resulting solutions
• Lead collaborative research projects, including stakeholder management and communication, organising collaborators, etc.
• Present research findings internally and externally in the form of presentations, papers, blog posts, or similar
• Work with users and customers to ensure project success
• Contribute to identification, design, and implementation of new features in the OpenProtein.AI platform
• Stay up to date with the latest research, models, algorithms, and wet lab techniques
  

• PhD with experience in ML/AI applied to biomolecules
• A demonstrated ability to operate independently and track record of publications in the top ML conferences or journals
• Strong communication skills
• Experience with the typical engineering stack: Python and pytorch, jax, or similar deep learning frameworks
• Deep knowledge of neural networks for working on biomolecules, especially protein structure encoding and decoding architectures, protein language models, and diffusion models
• Experience with the general bioinformatics toolkit: homology search, sequence alignment algorithms, structure analysis tools, phylogenetics, PSSMs, HMMs, etc.
• Knowledge of wet lab techniques for general protein engineering, e.g., mutational scans, affinity selection assays, structure determination methods, biophysical characterization methods, etc.
  
• Collaborative mindset with the ability to prioritize high level goals
  

• Hands on experience with antibody engineering or enzyme engineering in a high throughput end-to-end setting
• Experience deploying machine learning models in production, including cluster and GPU management, and API design
• Experience with molecular dynamics
• Strong product and visual design sense
• Experience deploying and using LLMs and RAG solutions
• Experience with grant applications, forming industrial collaborations, or similar

• Competitive base salary and equity
• Health and dental insurance