The Role: We are seeking a self-motivated, accomplished Machine Learning Scientist* to advance the state of the art in ML-driven antibody design. At BigHat Biosciences we frame antibody drug development as an iterative multi-objective optimization problem with a wet lab in-the-loop. A high-throughput weekly build-test-train cycle lets us rapidly evaluate and deploy a broad range of generative and predictive models on real-world therapeutics design challenges. Active learning and Bayesian optimization methods let us ensure these experiments also intelligently gather training data to continuously improve our models. As an ML Scientist excited about developing treatments for unmet patient need, you’re not just searching through biology for applications that fit the latest developments in machine learning. Rather, you’re using a deep understanding of real world drug development problems (arrived at with your interdisciplinary colleagues) to inform the development of the next generation of ML-driven protein engineering tools. *At BigHat we believe in titles that commensurate with skill set, relative organizational impact, and value contribution; more experienced candidates are encouraged to apply, with the understanding that responsibilities and title would adjust as appropriate.
Key Responsibilities
Design and implement the next state-of-the-art generative models of antibody sequence and structure, and predictive models of antibody properties, trained on proprietary internal datasets of thousands to millions of antibodies.
Develop multi-modality, multi-objective iterative protein sequence optimization approaches to lab-in-the-loop antibody design problems for validation and deployment in our high-throughput wet lab - at BigHat success is only declared upon synthesis of real antibodies with drug-like properties.
Share your findings at top-tier conferences and publish in leading scientific journals to advance the field of protein engineering.
Provide ML expertise and support for ongoing therapeutics programs, directly contributing to the development of new drugs.
Collaborate with our engineering team to ensure maximal efficiency in the automated deployment of our latest models to ongoing drug development programs.
Work closely with an interdisciplinary team of drug developers, wet lab scientists, automation specialists, data scientists, etc. to identify inefficiencies or potential improvements in the BigHat ML platform, and plan the next phase of ML research accordingly.
Preferred Qualifications
PhD in ML/CS or in the hard sciences with equivalent experience developing and applying novel ML methods and a strong quantitative background.
Publications in major ML conferences and/or leading journals, or extensive demonstrable track record developing and applying novel ML in industry.
Strong competency in Python, familiarity with PyTorch, and experience with modern software engineering best practices.
Excellent communication skills, sufficient biomedical domain knowledge to interact effectively with diverse scientific teams.
Enjoys a fast-paced environment and excels at executing across multiple projects.
Nice-to-haves include experience with protein structure modeling and biophysics, NGS data, familiarity with antibody biology, and experience training and deploying models on AWS.
