The Role
Develop generative and predictive machine learning models for antibody sequence, structure, and property design. Build multi-objective protein optimization and LLM-driven methods for lab-in-the-loop drug development, deploy models with engineering teams, and support therapeutic programs. Collaborate across machine learning, drug development, wet-lab science, automation, and data science teams to accelerate the creation of safer, more effective biologic therapies.
Summary Generated by Built In
The role: We are seeking a creative, ambitious Machine Learning Scientist or Engineer to advance the state of the art in ML-driven therapeutic antibody design.
At BigHat Biosciences our full-stack antibody drug development platform uses AI/ML to drive every stage from discovery to optimization. Our roboticized high-throughput wet-lab continually adds to our large proprietary datasets, which are piped through a custom LIMS++ 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.
You’re not interested in just git-cloning the latest NeurIPS pub and swapping out the dataset. Motivated by an enthusiasm for the possibility of addressing unmet patient need, and a curiosity about the underlying biology, you’ll apply your top-tier ML skillset to refine and expand this state of the art protein engineering platform. Success will mean not only hands-on methods development, but actively participating in the application of our platform to the accelerated design of new drugs for devastating diseases.
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 and 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.
Total Rewards
The salary estimated for this position is $150,000 - $200,000 + bonus + options + benefits. Compensation will vary depending on job-related knowledge, skills, and experience. Actual compensation will be confirmed in writing at the time of the offer.
About
BigHat Biosciences designs safer, more effective biologic therapies for patients using machine learning and synthetic biology. BigHat integrates a wet lab for high-speed characterization with machine learning technologies to guide the search for better antibodies. We apply these design capabilities to develop new generations of safer and more effective treatments for patients suffering from today’s most challenging diseases.BigHat is a Series B biotech outside San Francisco with a team-oriented, inclusive, and family-friendly culture. Our broad pipeline of wholly-owned and partnered therapeutic programs span many disparate indications with high unmet need, such as cancer, inflammation, and infectious disease. BigHat has raised >$100M from top investors, including Section 32, a16z, and 8VC.
Skills Required
- PhD in machine learning, computer science, electrical engineering, or a relevant scientific discipline
- Hands-on experience developing and applying novel machine learning methods
- Strong quantitative background
- Strong competency in Python
- Familiarity with PyTorch
- Experience with software engineering best practices, including testing and CI/CD
- Excellent communication skills
- Sufficient biomedical domain knowledge to work effectively with diverse scientific teams
- Familiarity with the state of the art in machine-learning-driven protein engineering
- Experience with de novo design
- Experience with NGS data
- Experience with Bayesian optimization
- Familiarity with antibody biology and drug development
- Experience training and deploying models on AWS
- Publications at major machine learning conferences
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
BigHat’s mission is to improve human health by making it far easier to design advanced, next-generation antibody therapeutics. Our AI-enabled experimental platform integrates a high-speed characterization or “wet” lab with machine learning technologies to speed the antibody engineering process. When applied, these design capabilities have the potential to drive the development of new generations of safer and more effective treatments for patients suffering from today’s most challenging diseases. BigHat is backed by Section 32, Andreessen Horowitz, 8VC, Amgen Ventures, Bristol Myers Squibb, Quadrille, Grids Capital, AME Cloud Ventures, Innovation Endeavors and Gaingels.
