Machine Learning Scientist

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.
• Develop, refine, and deploy agentic and LLM-driven optimization methods to further automate and accelerate our design-build-test loop.
• 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 and methods.
• Work closely with an interdisciplinary team of drug developers, wet lab scientists, automation specialists, data scientists, etc. - every therapeutics program at BigHat is heavily interdisciplinary.

Skills, Knowledge & Expertise

• PhD in ML/CS/EE or relevant scientific discipline, hands on experience developing and applying novel ML methods and a strong quantitative background.
• Strong competency in Python, familiarity with PyTorch (even without LLMs!) and experience with modern software engineering best practices, including not just agentic/LLM-assisted coding but testing, CI/CD, etc.
• Excellent communication skills, sufficient biomedical domain knowledge to interact effectively with diverse scientific teams.
• Energy and ambition - ready to dive into a fast-paced environment and execute across multiple projects.
• Familiarity with the current state-of-the-art in ML-driven protein engineering
• Nice-to-haves include experience with de novo design, NGS data, Bayesian optimization, familiarity with antibody biology and drug development, experience training and deploying models on AWS, and publications at major ML conferences.

Benefits