Machine Learning Engineer
MonarchAbout the role
We offer opportunities to do your life’s work while helping solve one of the most important technical and moral challenges of our time.
Full-time, in-office in Emeryville, California. $160,000–$260,000 annual base salary plus equity.
Build the reliable systems that carry our data from an assay recording to a reproducible model, an evaluated prediction, and a usable recommendation for the next experiment.
Key Responsibilities
- Own pipelines for ingesting, validating, versioning, and joining assay videos, metadata, compound records, model features, and experimental outcomes
- Build reproducible training and evaluation infrastructure with clear data lineage, model versioning, automated tests, and auditable outputs
- Turn research prototypes into dependable batch and online systems that can rank compounds and surface recommendations through our tools
- Monitor data quality, distribution shift, calibration, latency, cost, and failures as the number of labs and assays grows
- Design interfaces between computer vision, molecular models, active-learning systems, and the lab workflow
- Improve developer and researcher velocity without weakening scientific reproducibility or access controls
Qualifications
- Strong production software engineering experience in Python and modern machine-learning or data systems
- Experience deploying and operating model-training, feature, evaluation, or inference pipelines in a cloud environment
- Fluency with testing, observability, data validation, version control, and reproducible computational workflows
- Ability to work with large video datasets and structured scientific data
- Ability to collaborate closely with researchers while making sound engineering tradeoffs
Desired Attributes
- Experience with PyTorch, JAX, or TensorFlow and workflow-orchestration tools
- Experience on Google Cloud or with large-scale object-storage pipelines
- Familiarity with computer vision, molecular machine learning, active learning, or scientific data platforms
- Instinct for simple systems, explicit failure modes, and measurable reliability
Responsibilities
- Own pipelines for ingesting, validating, versioning, and joining assay videos, metadata, compound records, model features, and experimental outcomes
- Build reproducible training and evaluation infrastructure with clear data lineage, model versioning, automated tests, and auditable outputs
- Turn research prototypes into dependable batch and online systems that can rank compounds and surface recommendations through our tools
- Monitor data quality, distribution shift, calibration, latency, cost, and failures as the number of labs and assays grows
- Design interfaces between computer vision, molecular models, active-learning systems, and the lab workflow
- Improve developer and researcher velocity without weakening scientific reproducibility or access controls
Qualifications
- Strong production software engineering experience in Python and modern machine-learning or data systems
- Experience deploying and operating model-training, feature, evaluation, or inference pipelines in a cloud environment
- Fluency with testing, observability, data validation, version control, and reproducible computational workflows
- Ability to work with large video datasets and structured scientific data
- Ability to collaborate closely with researchers while making sound engineering tradeoffs
Benefits
- Equity
Skills mentioned
About Monarch
Building an alternative to insecticides is one of the most important technical challenges of our time. Most fruits and vegetables are sprayed with insecticides, including organics. The top three sprayed on these crops are toxic to the human nervous system. An estimated 35 quadrillion animals are killed yearly because of their use. And farmers lose tens of billions of dollars a year because insecticides often fail at their basic job: preventing insects from destroying crops. Monarch is developing a product that works—a spatial repellent that protects crops from insects, humans from toxins, and insects from needless harm. It will work by preventing insects from landing on crops in the first place. We’re building a genomic, molecular, and behavioral dataset from the ground up. Then applying computational chemistry and machine learning tools to predict which of the billions of potential compounds in nature trigger a ‘fly away’ signal from the olfactory neurons in the antennae to the smell center in the animal’s brain. From that unexplored data space, we’ll create the most effective products to protect crops and our long-term health.