Senior Machine Learning Research Engineer

The Role

Senior Machine Learning Research Engineer. As a Senior Machine Learning Research Engineer at Dyno Therapeutics, you will partner closely with our Machine Learning Research teams to design, develop, and optimize deep learning models for next-generation AAV capsid design. This role is deeply embedded in the research effort - focused on building, evaluating, and iterating on models that power our platform. You will bring engineering excellence to our ML research pipeline, helping scale our modeling impact and accelerate experimental design cycles.

Job Type: Full Time

Location: Watertown, MA or NYC (may consider remote candidates)

How You Will Contribute

As a Senior Machine Learning Research Engineer, you will collaborate with ML researchers to co-develop deep learning models, refine our experimental modeling workflows, and build high-leverage tools and data pipelines that increase team productivity. Your work will directly influence Dyno’s ability to generate and optimize novel capsids with therapeutic potential.

Responsibilities: 

• Work alongside ML researchers to design and train state-of-the-art models (e.g., generative models, classifiers, regressors) in PyTorch or JAX.
• Build research tooling to improve model development workflows—experiment tracking, evaluation metrics, and training diagnostics.
• Design, develop, and maintain scalable data pipelines for ML data from external (PDB, UniProt, etc.) and internal sources.
• Optimize training performance and model efficiency across diverse datasets and compute environments.
• Develop codebases that balance rapid iteration with long-term maintainability and clarity.
• Contribute to internal libraries for sequence modeling, data processing, augmentation, and featurization.
• Collaborate with domain scientists to understand modeling needs and experimental constraints.
• Stay current with new ML methodologies, evaluating emerging approaches for potential integration into Dyno’s platform.

Basic qualifications

• 2+ years of post-graduate, full-time work experience in ML-focused roles.
• Strong proficiency in Python, especially in ML and data science contexts.
• Experience with deep learning frameworks such as PyTorch or JAX.
• Familiarity with ML experiment tracking, model evaluation, and reproducibility best practices.
• Experience working with and building pipelines for scientific or structured datasets (e.g., sequences, graphs, tabular data).
• Alignment with Dyno’s core values.

Preferred qualifications

• Prior work in protein design, biological sequence modeling, or ML for biology.
• Experience developing generative models (e.g., LLMs, VAEs, diffusion models) or large-scale predictive models.
• Familiarity with training at scale using GPUs in cloud or HPC environments.
• Experience writing tools to support collaborative model development and review (e.g., dashboards, visualizations).
• Understanding of the biological context of sequence-function relationships.