Machine Learning Engineer
📍
Cambridge, MA
🧪
Entry level
Arena BioWorks, located in Cambridge, MA, is a new biomedical research institute focused on uncovering the mechanisms of human disease to identify opportunities for therapeutic intervention. The Institute's private funding model allows Arena to advance novel therapeutics by forming and supporting biotech companies up to the early clinical/series B stage.
As a machine learning engineer you will work with a team developing generative ML models for synthetic protein design. You will develop infrastructure and code for implementation of large language models applied to biomolecule design. The research team is investigating the tuning of DNA and protein language models for development of therapeutically relevant DNA sequences and enzymes. The machine learning engineer will, in addition to model implementation, will be involved in developing training data curation pipelines, and working closely with lab scientists generating high-throughput experimental data for model evaluation and fine tuning.
The candidate is expected to thrive in a multidisciplinary and highly collaborative environment. The desired candidate is passionate about developing and implementing machine learning models for development of therapeutic molecules. They also strongly value collaborating with scientists across teams and scientific areas and enjoy continuously learning from the expertise of their peers and colleagues.
Specific Responsibilities:
As a machine learning engineer you will work with a team developing generative ML models for synthetic protein design. You will develop infrastructure and code for implementation of large language models applied to biomolecule design. The research team is investigating the tuning of DNA and protein language models for development of therapeutically relevant DNA sequences and enzymes. The machine learning engineer will, in addition to model implementation, will be involved in developing training data curation pipelines, and working closely with lab scientists generating high-throughput experimental data for model evaluation and fine tuning.
The candidate is expected to thrive in a multidisciplinary and highly collaborative environment. The desired candidate is passionate about developing and implementing machine learning models for development of therapeutic molecules. They also strongly value collaborating with scientists across teams and scientific areas and enjoy continuously learning from the expertise of their peers and colleagues.
Specific Responsibilities:
- Work with the computational infrastructure team to optimize model training and inference environments
- Adapt and implement protein and DNA language models for synthetic protein design
- Consult with experimental scientists to evaluate data quality and optimize lab procedures
- Curate, preprocess and manage training datasets from public and internal sources
- Document code and communicate findings to cross-functional scientific teams and to the broader scientific community through written reports, publications, and/or internal and external research presentations
- Degree in computer science, bioinformatics, mathematics or related
- 2+ years of experience implementing machine learning models in an academic or industry setting.
- Proficiency in deep learning model development in Python and relevant ML libraries: (e.g. TensorFlow, PyTorch).
- Ability to work independently and as a team memberStrong interpersonal and communication skills
- Excellent analytical and critical thinking skills, both scientifically and in the ability to prioritize tasks, set deadlines, and adapt to shifting priorities
- Experience working with molecular biology data (e.g. DNA sequence, functional genomics)