Machine Learning, Summer Internship
The Role:
We are seeking talented, hard-working interns to join our Machine Learning team for the Summer 2026.
At BigHat Biosciences, we’ve re-framed antibody drug development as an iterative, machine learning–driven multi-objective optimization problem. Our roboticized high-throughput wet-lab continually adds to our large proprietary datasets, which are piped through a custom data management and orchestration layer to automatically update and deploy the latest models. This makes development of complex, net-gen therapeutics ‘trivially parallelizable’, at a pace which only accelerates as we develop better ML tooling.
As an ML Intern, you’ll work on developing novel ML models and proof-of-concept methods, with applications including multi-modal models of antibody biophysical properties, de novo and structure driven protein design, better protein language models, and active learning and bayesian optimization methods for embedding these models in our design-build-test loop. You’ll be mentored by an experienced ML scientist from our team and work closely with an interdisciplinary team of engineers, wet-lab scientists and drug developers to ensure your work is relevant for active drug development programs.
Key Responsibilities:
- Develop and evaluate a novel ML modeling or sequence optimization approach to solve an antibody engineering challenge relevant to BigHat’s therapeutics programs.
- Work with an interdisciplinary team of biologists, data scientists and machine learning scientists to gain sufficient domain familiarity to ensure your work is impactful.
- Document and present your results to relevant BigHat departments.
- Write production-grade code such that successful methods can be deployed and evaluated in the wet lab.
Preferred Qualifications:
- PhD or MS in progress, BS degree in ML, CS or in the hard sciences with significant ML experience and a strong math & prob/stats background. Truly exceptional undergraduates may be considered.
- Strong competency in Python, familiarity with PyTorch, exposure to modern software engineering best practices.
- Strong communication skills, sufficient biomedical domain knowledge to interact effectively with diverse scientific teams.
- Nice-to-haves include experience with protein structure modeling, de novo design, familiarity with antibody biology, and experience training and deploying models on AWS.