Bachelor's or Master's degree in Computer Science, Machine Learning, Computational Biology, or related field
2+ years of hands-on experience with PyTorch and/or JAX for deep learning applications
Strong proficiency in Python scientific computing stack (NumPy, Pandas, scikit-learn)
Experience with distributed computing and GPU optimization techniques
Familiarity with protein structure analysis or computational biology
Understanding of modern deep learning architectures and optimization techniques
Experience implementing research papers into production systems
Proficiency with version control (Git) and software engineering best practices
Responsibilities
Implement and optimize machine learning models for protein design
Build and maintain scalable data processing pipelines for large-scale datasets
Develop and deploy ML infrastructure for distributed training on GPU clusters
Collaborate with research scientists to translate ML approaches into production code
Design and execute ML experiments with clear hypotheses and analysis
Optimize model performance for large-scale protein tasks
Build tools for rapid prototyping and experimentation for the research team
Benefits
Collaborative work environment with leading researchers
Opportunity to impact protein therapeutic discoveries
Engagement with cutting-edge ML technologies
On-site role in innovative biotech hubs
Potential for career growth in a dynamic field
Full Job Description
Position
Manifold Bio is seeking a talented Machine Learning Research Engineer to join our growing AI team. You will work closely with our research scientists to implement, scale, and optimize machine learning systems that power our de novo antibody design platform and advance our protein design capabilities. Your efforts will contribute to building production-ready ML infrastructure that enables breakthrough discoveries in protein therapeutics. You will be expected to take ownership of engineering challenges in our ML pipeline, from data processing and model training to deployment and monitoring, while collaborating closely with our research team to translate cutting-edge ideas into robust, scalable systems.
This is an on-site role and can be based in either Boston, Massachusetts or San Francisco, California. Please only apply if you reside in these cities or are open to relocate.
Responsibilities
Implement and optimize machine learning models for protein design
Build and maintain scalable data processing pipelines for large-scale protein and molecular datasets
Develop and deploy ML infrastructure for distributed training and inference across GPU clusters
Collaborate with research scientists to translate experimental ML approaches into production-ready code
Design and execute ML experiments with clear hypotheses and rigorous analysis
Optimize model performance and computational efficiency for large-scale protein design tasks
Build tools and utilities to support rapid prototyping and experimentation by the research team
Required Qualifications
Bachelor's or Master's degree in Computer Science, Machine Learning, Computational Biology, or related field
2+ years of hands-on experience with PyTorch and/or JAX for deep learning applications
Strong proficiency in Python scientific computing stack (NumPy, Pandas, scikit-learn)
Experience with distributed computing and GPU optimization techniques
Familiarity with protein structure analysis, computational biology, or analogous problems in natural sciences
Understanding of modern deep learning architectures and optimization techniques
Experience implementing research papers or translating ML approaches to production systems
Proficiency with version control (Git), testing frameworks, and software engineering best practices
Strong problem-solving skills and ability to work independently on technical challenges
Excellent written and verbal communication skills for cross-functional collaboration
Preferred Qualifications
Experience training LLMs or diffusion generative models
Knowledge of cloud computing platforms (AWS, GCP) and containerization (Docker, Kubernetes)
Background in computational biology, bioinformatics, or structural biology
Experience with large-scale data engineering and ETL pipelines
Familiarity with MLOps practices and model deployment frameworks
This Role Might Be Perfect For You If
You are passionate about leveraging state of the art machine learning approaches to solve challenging disease areas
You enjoy translating research ideas into high impact, productionized, scalable code
You have rich AI/ML experience and are looking to pivot into biotech
If you're excited to build scalable ML systems that revolutionize protein therapeutic discovery, please reach out to [redacted].
