About the Role
SandboxAQ is seeking a highly motivated Senior ML Research Scientist to contribute their structure-based drug design expertise to our drug discovery team. The successful candidate will drive and contribute to cutting-edge research at the intersection of machine learning, biophysics, and quantum physics, support milestone delivery of customer engagements, and initiate, contribute to, and support the development of PoCs. Areas of specific interest include protein-ligand co-folding, ligand docking, and other machine-learning-based techniques related to structural biology and drug discovery. The successful candidate will be crucial in advancing the AQBioSim R&D roadmap, securing novel customer engagements, and developing key differentiated technology to support the long-term success of SandboxAQ and its AQBioSim division.What You’ll Do
* Research, develop, and implement modern deep learning approaches to relevant structure-based drug design problems in biopharma and drug discovery, in particular
o Development and implementation of generative AI frameworks (diffusion models, transformers, autoencoders aso) into functioning PoCs
o Development, implementation, and extension of ML methods for structure prediction such as AlphaFold, openFold, RosettaFold, uMol, or similar
o Contribution to the development of machine-learned force fields for classical simulation of molecular systems with applications in biopharma, material science, and more
* Develop and implement novel machine learning algorithms and computational models to analyze diverse biomedical datasets, including genomics, proteomics, ADME-tox, and more
* Evaluate the performance of machine learning models through rigorous validation and benchmarking against known data
* Collaborate with cross-functional teams of medicinal chemists, computational chemists, physicists, and engineers in the area of machine learning for drug discovery, chemistry, and material science
o Depending on experience: provide technical mentor ship and guidance to junior scientists, advise on projects and project roadmaps
o Create and lead ML research projects
* Support of client engagements
o Development and implementation of bespoke ML software solutions for client engagements
o Participation in client meetings, presentation of scientific results
* Stay abreast of the latest advancements in machine learning, cheminformatics, and biopharmaceutical research, and integrate relevant methodologies into ongoing projects.
o Write patents and publications highlighting the latest developments
o Attend conferences and participate in scientific collaborations
About You:
* PhD (or equivalent) in computer science, computational chemistry, computational physics, or any related field with a focus on machine learning
* 3-5 years (including PhD) of relevant research experience
* Proven experience applying ML to structure-based drug design as evidenced e.g. by co-authorship of research publications
* Proven track record of developing ML algorithms, in particular, deep learning approaches to structure prediction, force field development, and similar
* Strong communication skills and experience presenting scientific results to less educated audiences
* Excellent knowledge of modern DL architectures such as diffusion models, transformer models, flow-based networks, variational autoencoders, and similar
* Proficiency in programming languages and frameworks commonly used in machine learning and data analysis, such as Python or Julia, with relevant libraries and frameworks (e.g. jax, TensorFlow, PyTorch, scikit-learn, or others)
* Experience with software development in a dynamic startup environment, i.e. fluency with git, GitHub, cloud computing, coding best practices, code review a.s.o.
* Comfortable with navigating priorities in a dynamic startup environment
* Experience with antibody-protein structure prediction and binding, including over large datasets
The US base salary range for this full-time position is expected to be $175k - $286k per year. Our salary ranges are determined by role and level. Within the range, individual pay is determined by factors including job-related skills, experience, and relevant education or training. This role may be eligible for annual discretionary bonuses and equity.
#J-18808-Ljbffr