Back to Careers

Machine Learning Engineer – Drug Discovery

Position Description

Juvena Therapeutics, Inc. is a regenerative medicine biotech startup inviting applicants for a Machine Learning Engineer position who are excited to work as a core member of a team focused on the discovery and validation of novel candidate biologics for tissue regeneration and increased stem cell activity. They will design and implement new machine learning algorithms and collaborate with some of the top scientists in the field to reach new insights.

We integrate ML techniques into each stage of therapeutic discovery and development from lead and target identification through HTS to preclinical validation. Our technical innovations integrate and expand the latest approaches in proteomics, transcriptomics, computer vision, Natural Language Processing (NLP), Quantitative Structure Activity Relationship (QSAR) modeling, and neural networks to build an ML-enhanced drug discovery platform. With Deep Learning and other predictive modeling methods, we can identify and rank lead therapeutic candidates more cost-effectively and much faster than traditional methods. Applications include predicting phenotype and disease association from sequence-based and structure-based protein features, automated analysis of high-throughput screening microscopy images of primary human stem cells treated with candidate biologics, and quantitative analysis of tissue histology effects in preclinical models.

We are looking for an experienced Machine Learning Engineer to lead the development, validation, and interpretation of machine learning models with drug-development applications, engineer and integrate features from external and internal data sources, and to establish best-practice standards, processes, and tools supporting the data-science solution implementation lifecycle.

The position is full-time starting as early as possible. This is the perfect opportunity for someone interested in the exciting and fast-paced environment of a startup company to make a difference in human healthspan and develop cures for degenerative diseases.

Position Requirements

  • Lead the invention, evaluation, and implementation of machine learning technologies to discover novel protein-based therapeutics across a range of diseases and tissues
  • Lead data engineering to identify, extract, and create data features from large data sets for input into models. Data sources can include OMICS data sets such as single-cell transcriptomics, proteomics, microscopy images, protein feature databases, text-based literature, ontologies, etc.
  • Collaborate with scientists to analyze and select data modeling approaches, define model validation strategies, train and tune models, and analyze and resolve errors
  • Analyze and extract insights from modeling results; communicate them to the team and integrate them into the Juvena knowledge base
  • Establish best-practice standards, processes, and tools to drive a rapid data-science solution implementation lifecycle and track/manage data provenance and results reproducibility (e.g. ML and DE frameworks, git workflows, data management strategies)
  • Work cross-functionally to create the best possible pipeline of candidate therapeutics and the tools to scale out efficiently across multiple indications
  • Improve efficiency by automating data extractions, analyses, and reporting
  • Manage Google Cloud and AWS resources connected to relevant projects
  • Other engineering tasks as required.
  • Actively survey the forefront of published methods and resources for your field and internalize key aspects to the company


This position is a great fit if you possess:

  • MS or PhD degree in Computer Science, Artificial Intelligence, Machine Learning, Bioinformatics, or a related technical field.
  • 3+ years of machine learning or artificial intelligence development experience with demonstrated work products relevant to drug discovery (e.g. protein function prediction, phenotype prediction from molecular and other data)
  • Foundational knowledge of biology and experience with biological data
  • Familiarity with machine learning model development lifecycle, including study design, data collection and annotation, model development, model validation, benchmarking against competition, and rigorous statistical analysis
  • Proficiency in Python
  • Proficient in deep learning frameworks such as Tensorflow or PyTorch and analysis packages such as scikit-learn, scikit-image, OpenCV, and statistical analysis packages.
  • Proficiency in implementing workflows on cloud computing platforms
  • Industry or startup R&D experience

Apply Now

To apply for this position please complete the form below. Once the form is complete, email your CV and Cover Letter to with the title of the position as the subject line.