SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
BigHat Biosciences is seeking a Principal Machine Learning Scientist to lead the advancement of ML-driven therapeutic antibody design. The company operates a full-stack antibody drug development platform that integrates machine learning at every stage from discovery to optimization, backed by a roboticized high-throughput wet lab that continuously generates proprietary datasets.
In this role, you will design and implement state-of-the-art generative models for antibody sequence and structure, as well as predictive models for antibody properties trained on proprietary datasets containing thousands to millions of antibodies. You'll develop de novo design methods for generating initial hits to therapeutically challenging targets and create multi-modality, multi-objective iterative protein sequence optimization approaches for lab-in-the-loop antibody design validated in the high-throughput wet lab.
Beyond hands-on methods development, you will provide technical leadership and mentorship to other ML and data science team members, help set strategy for future ML research informed by deep understanding of BigHat's programs and real-world drug development challenges, and maintain expertise in the current state-of-the-art in ML-driven protein engineering. You'll collaborate with an interdisciplinary team including drug developers, wet lab scientists, automation specialists, and data scientists to identify platform inefficiencies and prioritize ML methods development. Success is measured by the synthesis of real antibodies with drug-like properties and contributions to peer-reviewed publications at top-tier conferences.
Required qualifications include a PhD in ML/CS or hard sciences with 5+ years post-graduation experience developing and applying novel ML methods, publications in major ML conferences or leading journals, strong Python competency with PyTorch familiarity, and modern software engineering best practices. You should have excellent communication skills, sufficient biomedical domain knowledge to work effectively with diverse scientific teams, and thrive in fast-paced, multi-project environments. Nice-to-haves include experience with de novo design, NGS data, Bayesian optimization, antibody biology, drug development, and AWS model deployment.
